Plugins

Manages local DeepSeek Harness skills in Settings and shows shared Agent skills as read-only.

Update management for the whole stack: compares DeepSeek Harness and every installed third-party plugin against npm and GitHub releases (semver-aware), shows a locale-aware banner (zh/en) with per-plugin update status, and provides one-click updates with automatic backup/rollback, temp-dir installs that never touch other packages, and a watchdog-guarded restart. A settings page adds per-plugin version lamps, live update progress, and banner/notification toggles. Zero-config on any machine.

Unified anchored agent preset for DeepSeek V4 Pro/Flash on the official API and opencode-go: Minimal-exact two-tool first-request bootstrap, model-aware Pro/Flash paths, and epoch-aware catalog management for long-session stability.

MCP bridge to gemini.google.com: vision analysis of images and videos, Imagen image and Veo video generation, and conversation management using the logged-in browser session with no API key.

Bottom info bar for the DSH Web UI: provider/model, live balance, peak/off-peak pricing with countdown, and real persisted per-session spend in a single line.

Codex-style drag-drop: drag any file into the DSH web GUI, it lands in ~/.dsh-dropbox, and the path is inserted into the composer as a whole blue chip.

OAuth 2.1 MCP client for Streamable HTTP servers: add a connection in Settings, sign in through the browser (PKCE with dynamic client registration), and have its tools registered in DSH, with tokens kept in the credential service and the connection written to the profile.

Use your ChatGPT subscription in DeepSeek Harness through OpenAI's Codex sign-in flow

DeepSeek Harness plugin that connects to a PowerContext Server over HTTP for recall, memory, handoff, experience, and skills.

模型路由与成本优化器：简单问题 flash 直答、故障自动降级、会话 token/缓存/成本实时面板 | Model router & cost optimizer for DeepSeek Harness: flash quick-answers for simple questions, failure fallback, live token/cache/cost panel

A second brain for your DeepSeek Harness agent — strong-model review before risky tool calls, plus 67 models from one wallet. No accounts, no API keys.

Claude Code /rewind for DeepSeek Harness: git-first workspace snapshots before every mutating tool execution, turn-boundary session forks, and a one-shot /rewind command that restores files and forks the session back to a checkpoint.

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.

Auto-log failed tool calls across native tools, PTC run_code, and inline invocations: dedup and count root causes into a skill so repeated mistakes fade.

Skill pool manager in the Settings sidebar: enable/disable, folder batch import with rename-conflict prompts, state-driven one-click DSH-spec check & auto-fix, system/project scope labels.

Select part of a conversation and ask about it in a right-side side chat; bring AI replies back to the main chat directly or as a summary.

A right-side floating panel and /context command for DeepSeek Harness — a live donut chart of context token usage, allocation, and estimated cost.

All-in-one DSH extension center in Settings: manage skills, MCP servers and plugins, a Plugin Market (curated + GitHub search, npm one-click install), and an Add-ons block to install, disable, uninstall and update companion features together.

Edit the host-wide global instructions (~/.dsh/AGENTS.md) from a dedicated Customize page in Settings - every session on this machine applies them.

Feishu (Lark) UI for DeepSeek Harness — a panel-driven control console: every slash command is a button on the ⚙️ control-panel card, in-card approvals and questions, live streaming cards, and one-QR app setup.

Model high-availability failover (quarantine, circuit breaking, probe recovery) and subagent orchestration (fanout/pipeline/supervisor) with bilingual settings UI.

Multi-platform Agent Skills monorepo that mounts as a DeepSeek Harness profile bundle, exposing Chinese writing, Git, plugin-dev, taste, and semantic-linter skills.

Render Mermaid code fences in DSH Web chat messages as lazy-loaded SVG diagrams with strict sanitization and light/dark theme follow.

Reads assistant replies aloud via free Edge TTS or your own RVC voice models: read-aloud buttons + auto-read, adaptive chunked progressive playback (gapless long reads), one-click voice-pack installs from a registry, and a portable RVC runtime.