Plugins

Expose DeepSeek Harness agent capabilities as an MCP server, so an external MCP client (e.g. Hermes) can drive Harness to execute coding tasks. Hermes = brain, Harness = arms.

Windowed, reversible context management for DeepSeek Harness; replaces Basic compaction.

DeepSeek Harness 的 MCP 服务与 Skills 管理器：面板里增删改 MCP 行、扫描导入其他 Agent 配置、管理 Skills。Web 与 Desktop profile 通用。

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.

Bitmap-frame context compression plugin for DeepSeek Harness: renders discarded conversation history into pixel-font PNG frames for vision-capable models.

Resumes turns interrupted by a DSH host restart: hooks agent activation (once a session is live), reads the crash-repair turn/end, and sends a continuation that requires verifying real-world state first rather than assuming a side effect succeeded or failed. Permanent failures (AUTH, QUOTA, context overflow) are skipped, with a cross-restart budget, adaptive backoff and a minimal-context payload.

Select text in the DSH web UI to stream a translation and an explanation of what it means in that specific context, read against the conversation it came from; the panel keeps a replayable history and can be promoted into a full session.

Markdown visual enhancement and session workbench for DSH Web Composer: live syntax presentation with caret-row source reveal, deterministic local completions and diagnostics; long pastes fold into persistent chips with inline context or file-mode delivery (@path across 50+ extensions) plus sidebar LLM rewrites (stop, preview diff, undo/redo); real-time context map with token gauge, composition breakdown, per-turn growth chart with anchor lines, in-place /compact, and turn forking.

Drive your local DSH from WeChat: a self-hosted iLink bridge over a persistent ACP session (context lives in DSH and is resumable), phone conversations grouped into the desktop workspace, with image recognition, file messages (Excel/Word/PDF, parsed by the agent itself) and voice transcripts. Access defaults to strict (only registered devices are served); the phone channel's permission preset is wide by design - see the README security section before sharing the bot.

Meeting rooms for DSH sessions: joining a room grants the right to convene and the duty to attend, and a session belongs to at most one room. Convening forks each participant in with its own completed-turn context and with its tools stripped, a moderator that carries no context chooses the speakers, and every turn is appended to disk as it is spoken. After adjournment each participant receives its own minutes as a user turn and resumes work.

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.

21 read-only lifecycle governance tools in one self-contained DSH plugin: task tiering, state/plan/evidence validation, gate precheck and aggregation, release/install audits, context and progress analysis, critical path, resume reconciliation, and a mutation preview that always denies execution. Installs from npm as @240xu/dsh-tech-lead.

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

Right-click menus for the DSH Web UI — copy, cut, paste and select all on text and input areas, plus copy path, reveal in the file manager and open with the default app on file references and links.

Fronts stdio MCP servers with three router tools (list_capabilities, describe_tool, call_tool) so schemas load on demand instead of riding every request; shapes every tool result through a deterministic output ladder that archives the original first (retrieve_spill reads it back); prices tool groups in tokens and can hide built-in groups per agent. Bridges to a standard-library Python router, so Python 3.9+ is required.

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).

Model-autonomous context compaction for DeepSeek Harness: a mind_map tool surveys the agent context surface (stable seq ids, roles, token weights, clear-boundary markers, the clear-mind playbook), a clear_mind tool replaces a chosen conversation-history span with a model-written checkpoint through the native compaction transaction, call and result pairs self-collapse into one-line tombstones, and a proactive reminder nudges the model when the context grows long or a turn runs too many steps.

One-click draft polish for the DSH composer: rewrites your spoken draft into professional wording, sends only the draft snapshot (never conversation context), and never blocks sending if the LLM is unavailable.

Same-origin in mechanism with the two loudest lines in context compression. The code-skeleton gate follows the skeletonization approach of Headroom (Apache-2.0), whose published headline is 20% fewer tokens for coding agents and 60–95% fewer tokens for JSON, same answers. The estimator channel follows TokenPilot (arXiv:2606.17016), which reports up to 60% lower cost for long-session agents. Both figures are theirs, quoted as-is; this plugin ships no benchmark of its own and claims no reduction of its own. What it adds for DeepSeek Harness: choose a compression profile, set the Auto Compact trigger level and toggle code-skeleton compression from one settings section, with exact DeepSeek V4 tokenizer measurement, same-revision count verification, and fail-open behaviour that keeps the original tool results on unsupported models.

Adds a composer button that optimizes the current prompt or designs the next one from the current session and project context.

FDE toolbox bundle: installing this one plugin pulls in a curated set of common dsh plugins (git server, WebDAV mount, knowledge base, scheduled tasks, auto-resume, UI tweaks, auto-retrospection, file manager, smart titles, task board, plugin market, context trimmer, IM bridge, sidebar enhancements), with a panel showing install status and one-click gap-filling.

Alibaba Bailian (DashScope) model catalog preset + auto-adapter for DeepSeek Harness — reasoning effort levels, thinking budgets, context windows, auto-adaptation of existing Bailian routes, a configurable context ceiling

Out-of-tree dsh plugin: GitLab, GitHub, Gitee, Gitea, and Bitbucket tokens stay out of the model context, stored encrypted (AES-256-GCM) in a plugin-owned file; the model calls forge API tools on demand, and the web settings page manages sites and tokens.

One MCP tool instead of every schema you own — a lazy capability broker that cuts resident tool context by a measured 94.4%. Search, inspect, enable and call MCP servers and skills on demand.