Plugins

Reference verification for DeepSeek Harness (参考文献真实性检查器): the reference_checker model tool checks a paper's bibliography (.pdf/.bib/.tex/.txt or pasted text) against Crossref, OpenAlex and arXiv, reports found / partial / not_found / error per entry, and emits corrected citations in the input's style (APA, GB/T 7714, IEEE, Vancouver, MLA, Chicago, Harvard, ACS, BibTeX).

Proactive per-provider token-bucket rate limiting that queues over-limit requests before they are sent, preventing upstream 429 errors.

Native tools for an Obsidian wiki vault: wiki_query, wiki_write, wiki_rename, wiki_scaffold, wiki_archive, and wiki_lint cover BM25 search with link-graph context, bookkeeping writes with sha256 source tracking, vault-wide renames, mode scaffolds, source archiving, and health checks — with cross-process locks and optional git auto-commit.

Read-only Git Graph in the native DSH Web sidebar, with commit history, branch and tag refs, file diffs, two-commit comparison, and full historical source.

12 tested engineering skills (git commit, code review, test-first, plugin dev, debugging, changelog, PR review, task breakdown, and more): every SKILL.md passes a format validator aligned with the official skill rules plus an isolated load smoke test.

Activity heatmap in the DSH Web sidebar: GitHub-style grid of daily commits, token usage, and estimated spend, with a today stats line for all-session token totals, cache hit rate, and per-model auto-priced cost.

Adds a "Compact and run" action to the DSH Web plan-review card, which compacts the history submitted before the plan into a checkpoint and then approves the plan.

Literature research toolset registering 26 model tools over PubMed, Europe PMC, OpenAlex, PubTator3 and Semantic Scholar: field-syntax search, ID conversion, bibliographic lookup, citation formatting, MeSH and related-article walking, PubTator bioconcept resolution and relation queries, Europe PMC and Semantic Scholar paging, full-text retrieval, and open-access PDF discovery with optional download. A unified search deduplicates hits across sources and orders results by cross-source hits, then relevance, then citation count; a session knowledge graph with PubTator concept enrichment commits to a persistent user graph and renders as Mermaid. Most sources need no key.

Keeps project decisions in plain markdown instead of chat history: one main document plus per-module documents, every entry carrying a file:line citation. The agent interviews you to turn open questions into settled decisions, and a five-dimension score (task complexity, extensibility, maintainability, code quality, reusability) is derived from the documents and shown on a button beside the model picker. A session can bind several projects; projects are sized small/medium/large, which widens the entry limits, and a reusable-pipeline section in the main document is injected when its trigger words appear.

Exposes the local DSH web GUI to one chosen CIDR range only (Tailscale by default) instead of binding 0.0.0.0: the proxy listens on addresses inside that range, rejects peers outside it, and admits clients by either a tokenised URL or a 4-12 character alphanumeric access code. Remote pages can be forced into a phone layout without changing the local UI, and the official appearance, font size, transcript view, code view and performance settings can be stored in the plugin config and re-applied on every remote page load.

Composer and sidebar helpers in one plugin, each switchable in Settings: a git Changes panel (uncommitted / unstaged / staged / branch diffs), ↑/↓ input history, Shift+Tab /plan toggle, one-click ▶ Continue after a stopped or failed turn, drag-and-drop queue reordering, Copy deeplink, Auto Review "Allow for this chat", project status markers with active projects first, background notifications, 11 extra UI languages and automatic updates from GitHub releases through the plugin manager.

Brings SenseNova (日日新) models into dsh with a per-key rotation pool: paste any number of API keys and requests rotate across them, a 429 rate-limit immediately retries on the next key with per-key exponential-backoff cooldown, local RPM pre-throttling avoids the limit instead of reacting to it, and an exhausted pool answers 503 with Retry-After so a 429 never reaches the caller. Ships a built-in model catalogue that works offline and refreshes from /v1/models, plus a settings card with masked keys, per-key probing and removal.

Hierarchical Claude Code-style memory: user + project scopes (project memories committed to git for the team), MEMORY.md index auto-injected at session start, context-window guards, pure files.

Concurrency guard and monitor for DeepSeek Harness: FIFO queue when concurrent model requests reach the limit, per-day persisted stats with error-kind classification, and interruption detection for abandoned streams.

WeChat Official Account source collector: QR-login credential profiles, rate-limit-safe crawling with cooldown, RSS second water source, and secret-safe handoff to ContentStudio.

Rate-limits LLM requests per provider and per model using a reservation-based token bucket, with queue or reject modes, plus gateway identity rules that rewrite user-agent and inject custom headers.

Makes plain Enter insert a newline in the composer and Ctrl/Cmd+Enter submit, toggleable in settings.

AgentDuel is a code-battle game. This plugin lets you complete the entire game loop inside DSH: manage deathmatch characters and capture-the-flag teams, submit agent code, start battles, watch replays, and use DSH conversations to keep improving agents based on battle results.

Enhanced vision toolbox: 14 pixel-level vision tools (describe, ground, detect, crop, pixel-diff, OCR, long-screenshot OCR, vectorize, colors, cutout, screenshot, present, materialize, html-screenshot) driven by one OpenAI-compatible endpoint, with clean \[图片: path] bridge markers, content-safety classification and rate-limit auto-retry.

Git history visualization for the dock workbench: swimlane commit graph, branch and tag management, stage/commit/push and remote operations.

Vision MCP and DSH bundle for text-only DeepSeek: analyze_image, analyze_clipboard, compare_images and vision_status tools, a visual settings page, free GLM-4.6V-Flash by default, result caching and rate-limit tolerance; keys stay out of logs.

Control plane for the harness's own Agent Teams: members are ordinary independent sessions created through the same seam the GUI uses, each with its own model, so they open and continue like any other conversation while a sidecar roster and task board coordinate them. Task entries carry a definition of done, a member's completion is submitted and waits for the Lead's review, and availability tells idle apart from awaiting-review or a failed last turn. With delegationEngine=auto it uses independent sessions, continuable subagents, or the kernel roster depending on what the composition provides.

JetBrains-style IDE workbench in the DSH sidebar: Project file tree, Commit panel, Git history with a swimlane graph, a real PTY terminal and an embedded editor with Markdown preview and Find in Files, plus chat file links and send-to-chat references.

Two-way bridge between GNU Emacs and a running DeepSeek Harness session over loopback HTTP + SSE: submit prompts, stream replies, manage sessions and workspaces, and answer ask-user/approval prompts from Emacs, with a Plugins-page card that installs the Emacs package.