Plugins

A document preview / edit / management plugin for DeepSeek Harness. It provides a VSCode-style "Document Center" workbench inside the DSH Web GUI: a file tree on the left, click-to-preview, editable code & Markdown with Ctrl/Cmd+S save; and exposes three document tools (doc_read / doc_edit / doc_create) to agents, letting models read and write workspace documents through natural language.

Decision-and-goal memory with lineage: explicit commands and a model tool record decisions deterministically, a status card re-anchors them across compaction, a lossless event stream with BM25+jieba retrieval backs it, and a scenario-level fidelity regression suite gates releases.

Ownership-checked tools and HTTP routes to list, release and permanently delete subagent sessions, with automatic web UI refresh after deletion.

Full-screen lightbox for chat images with zoom, drag pan, download, and keyboard or touch navigation. Images returned by the display_image tool render inline in chat.

Fourth permission preset for dsh: unconfined, GPU-capable sessions (danger-full-access) with per-operation user approval for writes outside the workspace or to protected paths (.git/**, .env*); implemented purely as a bundle over the official tools/pre-execute ask hook, no core edits.

Aggregated web-search provider for the built-in web_search tool: one prioritized queue over nine providers (AnySearch, TinyFish, Tavily, Brave, Exa, Firecrawl, Jina, SerpApi, Serper), with multi-key rotation per provider, ordered fallback on failed attempts, and a live settings card.

Skill studio for DeepSeek Harness: visualize every agent skill (name, description, source, nested flag, model/user invocation), view and edit the full SKILL.md body, toggle model/user invocation, and mine DSH session logs to extract reusable personal skills that the agent auto-loads — from the web settings panel and via skillmgr_* / skillmgr_extract_* tools.

One-click health check for DeepSeek Harness: 0-100 score, plain-language issue list, and safe reversible fixes via the profile's cordis.patch.yml.

IDE-style run configurations for DSH: save LLM prompts and shell commands as reusable run configs (global or per-workspace), run them from the session header or the new-session page, and manage them via the task_run_config tool with approval-gated writes.

AI-native music player plugin for DeepSeek Harness: aggregates NetEase Cloud Music, QQ Music and KuGou search with cross-provider playback fallback, renders word-by-word karaoke lyrics synced live over USB HID to HALO PIXELBAR speakers, and exposes search, playback, queue, alarm and speaker control as model tools.

Manage Windows hosts over WinRM from a web panel and seven agent tools with PowerShell exec, service and process control, SMB / chunked file transfer with SHA-256 verification, and cluster execution.

Vets local, npm, and GitHub plugin source before installation, blocks configured high-risk tool calls at runtime, audits output secret patterns, and writes HMAC-chained local audit logs.

Source-aware prompt injection guard for DSH: tracks untrusted turn context, detects injection signals, scores sensitive sinks, and blocks high-risk tool calls with explainable audit logs.

A `/backstory` command and tool that annotate each line with the git commit that last touched it and the agent turn + prompt that wrote it, from a persistent per-line ledger (drift-proof by content hash), DSH-* commit trailers, or the live session log.

Agent-managed procedural memory: a skill_manage tool that creates, patches, disables and deletes the agent's own skills in user or project scope, with delete guards (agent-created marker, pin, path confinement) and a trigger-discipline prompt.

Windows desktop UI context picker for Codex, DeepSeek Harness, and MCP clients: select windows, UI elements, or screen regions with hover highlighting, UI Automation, screenshots, and local OCR, then review and approve Markdown/JSON context before output.

Cross-session memory for DeepSeek Harness via the official storage domain: memories persist through ctx.storage (storageDomain table) and are injected into the system prompt through a registered section (memory:recall), with memory_save / memory_forget tools so the agent reads and writes its own memory (maxMemories configurable).

DeepSeek Harness (dsh) plugin embedding the fin-trace agent loop — multi-hop relationship reasoning over a financial knowledge graph, exposed as async tools (start/status/cancel)

DeepSeek Harness plugin: Superself's `self` CLI as model-facing tools plus a /self command — cross-session, cross-project project state for agents.

Tavily Search API as a web search provider (settings toggle with DeepSeek fallback, keyless search) plus a Tavily MCP bridge: keyless search and extract tools, crawl and map with an API key.

Firecrawl MCP bridge: hosted Firecrawl MCP server with keyless search, scrape and parse; an API key unlocks the full tool surface including crawl and map.

Windows minimal agent preset for DeepSeek Harness: fixed one-line persona, three tools, no runtime context.

Adds a subagent_routed tool that runs a one-shot subagent fully mounted on any agent preset from any session, with per-call model/provider override and a model-availability pre-check.

Multi-backend web_search provider (Exa + Firecrawl) for the built-in web_search tool, with automatic failover, per-backend 429 cooldowns, and key-free anonymous access.