Plugins

DeepSeek Harness 插件：一键安装「极简模式 (Git Bash)」agent preset —— 把 DSH 自带极简模式中的 bash 调用映射到 Git for Windows 的 bash（MSYS），让 Windows 上的极简模式真正可用。

Project-scoped cross-session memory: seven-layer SQLite store (soul/user/project/fact/lesson/rules/topic) on node:sqlite, cache-friendly first-message injection plus per-message keyword hits, memory_remember/search/find_similar/read/update/project tools, and idle-window consolidation ("dream") with peak-hour suppression. Prompt texts ship as per-language data files — the framework supports multilingual users.

Bounded, layered, approval-gated, auditable cross-session memory: a typed `ctx.memory` seam with a zero-dependency SQLite provider, a `memory` tool, and frozen snapshot injection, plus the dsh-memory-protocol v1 rehearsal with an adapter registry and a distributable conformance suite.

UltraCode-style multi-agent orchestration: a generatable, savable, governable, observable, resumable workflow layer.

Long-term memory for DSH agents — durable, inspectable memories with recall, search, browse and knowledge-graph tools, import from ten other AI coding tools, and a settings page.

Adds a strip above the composer to recall sent-but-unread (steering) text messages before the model reads them.

Dynamic workflow for DSH (placeholder).

Roleplay workspace for DeepSeek Harness: import SillyTavern/TauriTavern character cards or author one from scratch through an interactive flow; turn a long TXT novel into a playable card with either an intensive or a coarse reading pass; the main agent consults worldbooks on demand, and prose is read in a dedicated tavern reader tab; explore multiple worldlines inside one conversation (regenerate, edit-and-send, explicit clone); scoped style presets with 16 built-in styles, a character agent cluster, a standalone decision card, and card or novel export; long stories hold together through a frozen settings prefix, a hard-cut context window, traceable director notes and keyword/semantic/hybrid recall, with embeddings either online or fully local. Targets Harness 0.1.2-alpha.3 and applies its documented compatibility patches.

Skills and optional MCP rows for eleven marketplaces: price comparison across Wildberries, Detsky Mir and Yandex Market, plus per-source search, product cards and reviews, including Ozon, Avito and AliExpress. The 14 skills load on install; both MCP rows stay disabled until RU_MARKETPLACE_MCP_DIR points at a local clone, which needs Python 3.12+ and uv.

Cleans AI traces from Russian text: finds chatbot copy-paste artefacts (ChatGPT, Gemini, Grok, Perplexity, DeepSeek), strips hidden text marks (zero-width characters, invisible layout; shadow scan catches markers split by invisibles), and rewrites the text into natural prose on request; 40 regex markers, 38 with full evidence-registry entries; 156 gates, 530 tests; offline, text-only bundle (binary metadata removal lives in scripts/).

Auto-resumes interrupted DSH Web requests: sends a queued 「继续」 after network, timeout or host-crash failures, with error classification, adaptive backoff, templated continue text and browser notifications.

Rewind conversation and workspace state, powered by a persistent Change Ledger.

baro as a DeepSeek Harness subagent provider: delegate a multi-story goal, get parallel execution, independent review and a verified outcome back — with a live run panel in the sidebar

Inline-edit and recall your own user messages in dsh web — lazily and seamlessly, with a version pager and per-session draft persistence.

Base aggregate for DeepSeek Harness Desktop features: Web UI collection, plugin market, Codex Connect, and reasoning controls.

The memory that dreams — cross-session memory for DeepSeek Harness: recalls you across sessions, auto-consolidates in its sleep (autoDream), freezes conflicting memories for your review, and keeps a replayable audit trail. Offline-first local semantic search over SQLite with human-editable Markdown mirrors, an entity graph, an interactive memory panel, plus an external API and CLI.

Personal center for DeepSeek Harness: cross-session usage statistics, per-model cost estimation, global custom instructions, a global font-size adjuster, a data-driven desktop pet with bitmap & vector skins, and a conversation status overview, all local and offline.

Chat meme stickers: text-only send, mood auto-send, QQ/WeChat-style picker, auto-learn, custom packs.

Profile-wide DSH governance and routing with a Web Control Center for responsibility and evidence inspection, plus compaction, scoped semantic memory, safety continuity, and verified delivery; compatible with DSH 0.1.5-rc.1.

Model-driven context compression (Active Context Pruning) for DeepSeek Harness: the model decides when and what to compress.

Non-commercial day/night whale-girl skin for official Harness rc.7: current no-viewport-frame layout, paired crystal-workshop and moon-tide scenes, chibi companions, translucent ornaments, and lightweight ambience.

Claude Code-style declarative permission rules: ordered allow/deny/ask YAML rules matching tool names, arguments, workspace paths, and agent identity on the tools/pre-execute waterfall, with full session-log audit, dry-run mode, and hot reload.

Code-first React and TypeScript task apps rendered inline, in Canvas, full screen, or on localhost, with interaction state available to later agent turns and approval-gated MCP and API access.

The memory that dreams — cross-session memory for DeepSeek Harness: recalls you across sessions, auto-consolidates in its sleep (autoDream), freezes conflicting memories for your review, and keeps a replayable audit trail. Offline-first local semantic search over SQLite with human-editable Markdown mirrors, an entity graph, an interactive memory panel, plus an external API and CLI.