Plugins

A DSH-first Rust/ratatui agent TUI with streamed tool calls, subagents, durable sessions, and a Cordis-extensible client UI.

Sidebar billing dashboard: real usage aggregated from session logs (per-model and per-day calls/tokens/cache), cost estimated in CNY from a current multi-provider pricing catalog, subscription-plan (coding/token/agent) routes exempt, and per-provider health dots.

Renders agent HTML output as real UI in the DeepSeek Harness web GUI, with visual cards, KaTeX math, Mermaid diagrams, built-in open-source fonts, and design-spec injection.

In-chat read-aloud for DeepSeek Harness: tap to read, pause and resume AI replies with natural Doubao TTS voices (BYOK), reading only the final answer with code, tables and diagrams filtered; local engine, plugin keeps no API key.

DSH适用的Codex风格的思考强度滑块，以及大肥鱼跑步滑块。Codex-style model and reasoning-effort slider for DeepSeek Harness

Read-only runtime management panel for the official DSH MCP client: connection status, registered tools, errors, and reconnect counts through the /mcp command and a Settings tab, with sanitized display and enable/disable patch suggestions.

Inject deployment-configured system-prompt sections and reference exchanges into every conversation request via stream interception, with a web settings panel.

Search 65,600+ API docs from 20 Chinese open platforms through five read-only tools and a runtime skill.

A persistent agent team for long-running collaboration in DeepSeek Harness: durable agent identities, per-project Workspaces, responsibility-bearing Channels, and Task Threads chaining session agents.

Word alternatives and underscore-gated fill-ins in the composer. End a line with _ and it is filled; misspellings are flagged as you type. Routes through the model dsh is already configured with, so it needs no API key.

Task board for DSH: create tasks with project and model assignment, run them manually or on cron schedules; new sessions in a project automatically pick up its todo tasks and move them to in-review when done.

A persistent agent team for long-running collaboration in DeepSeek Harness: durable agent identities, per-project Workspaces, responsibility-bearing Channels, and Task Threads chaining session agents.

Codex-style workflow auto-collapse: finished turns fold into a single "processed in Xs" row leaving only the final answer; tool calls and think blocks collapse into live-summary chips that follow streaming; expand level by level, fully reversible on uninstall.

Embracing All Creation (Plugin Suite) — Dedicated to the Harmonious Coexistence of Hundreds of DSH Plugins / 揽尽万象（插件整合包） —— 致力于让数百个DSH插件和谐共存

Drive the Unity Editor from DSH through the official unity CLI: live-Editor scene commands, in-Editor C# eval and runtime command discovery over a warm unity shell session, plus a raw CLI escape hatch for project creation, tests and builds. Mounts Unity's official skill collection alongside its own Unity workflow and Asset Store skills.

Shared multi-agent task board (create/claim/transition/query) over a Cordis service key.

Export the append-only session log as human-readable Markdown or HTML, grouped by trajectory source.

Keeps a local TinyTitan model server reachable from the harness: refreshes the llm-pi-ai route from the installed models and mounts a compaction backend that does not think.

Trace Compare & Live Maze: draw the agent's real exploration — main path, failed or dead-end detours, backtracks, and subagent branches — on one wall-clock timeline; upload 1–2 session logs for a same-axis compare, or watch it grow live in a session tab.

Deep-read books and articles in five modes (quick, deep, knowledge map, Feynman, full book) with claim-evidence-data reports, Mermaid/XMind mindmaps, batch comparison, budget preflight, transparent background-job progress, and MD/HTML exports from URLs, files, or pasted text.

Cross-session memory engine for DeepSeek Harness: SQLite store + human-editable Markdown mirror, autoDream consolidation, offline semantic search (local vector/rerank/clustering), entity-attribute-timeline, Sleep Mode, custom-model autoSummarize, and 7 memory tools.

Per-model reasoning-effort and input-modality configuration for third-party providers: suggestions fused from a model knowledge base and raw /models endpoint evidence with confidence labels, edited inside the official Models page card.

Floating DSH desktop pet with 12 authored state animations for requests, tools, compaction, archive and prompt enhancement; live context occupancy; a persistent cross-session Lifetime Ledger; per-provider/model totals, hourly trends and 7/30-day views; dark/light theme switching; optional cost estimates (off by default) with a visual price editor and monthly budget alert; client-side skin ZIP import; JSON/CSV usage export; snapshot-only panel reads with background incremental indexing; and opt-in prompt enhancement with editable preview and DSH composer submission.

Puts the Markdown documents, source files, images and video that already exist anywhere in the session workspace into the DSH sidebar, ranked by relevance to the current conversation. The default lexical mode matches your recent messages against title, summary and body locally with IDF weighting (BM25) — no model calls, no network, nothing leaves the machine. The list comes from scanning the workspace rather than from a recent-files list, so restarting DSH or opening a new session does not empty it. Results are organised into a three-tier reading order (primary / supporting / related) with a verifiable reason on every row — which field matched, which document cites this one — and one click opens an in-place preview: Markdown as rendered text, relative-path images actually drawn, source code with the host's own syntax highlighting, video streamed over HTTP Range. The same Context Pack is exposed to the agent as a knit_docs tool. Later versions added read evidence and lifecycle tracking (attribution is frozen at the moment of reading), pin / exclude (exclusion applies before retrieval, and is undoable), relation evidence (references / imports / tests, with line numbers) and an incremental index reused across restarts. Since v0.23 there is also an optional hybrid mode: it is off by default and only runs once you configure an Ollama or OpenAI-compatible embedding provider yourself. When it runs, what leaves the machine is your query text plus each candidate file's title and summary — a Markdown summary is an excerpt of the body's first paragraph (at most 60 characters), a code file's summary is its workspace-relative directory, and an image or video contributes its file name; full bodies and absolute paths are not sent, and a loopback provider keeps everything on this machine. Since v0.24 it also associates uncommitted changes: a read-only git status (fixed argv, no shell, whitelisted child-process environment) combined with the same reference / import / test / mention evidence shows which files a change is likely to drag along, and it is off by default. The benefit of semantic retrieval still awaits a real-provider run, so no recall improvement is claimed.