Plugins

Hover timestamps for DSH web chat nodes — start–end (and duration) on Think, Bash and every tool/step row · 在 web 界面 hover Think/Bash 等会话节点行时显示开始-结束时间与用时的 DeepSeek Harness 插件

Free anonymous OpenCode Zen models inside DeepSeek Harness (DSH): native LlmAdapter, no API key, no child process; optional Go sidecar included

Workspace-isolated durable memory for DSH, with searchable, auditable, correctable, and removable workspace memories plus controlled global memory.

在对话中直接渲染交易图表：trade_chart 工具 + 内联 SVG 图表卡片（K线/折线/柱状/面积，含成交量副图、MA 均线、波段与自由标注、滚轮缩放平移），数据来自行情技能（longbridge / hithink）。

dsh plugin: routes ask-user questions to every interaction surface bound to the asking session (TUI panel, Feishu card, web, ...) — first answer wins

Garmin Connect 运动健康 AI 教练插件 for DeepSeek Harness — 同步活动/健康/HRV 数据 + AI 训练建议 + 训练计划 + 训练日记

Tavily-backed web search provider for DeepSeek Harness (dsh)

AnySearch web search provider plugin for DeepSeek Harness (dsh)

dsh plugin: keep llm-pi-ai provider routes' model lists in step with the pi.dev gateway, written through the official settings seam

dsh plugin: token-efficient prompt-side shim for the official MCP client — folds mcp__* tool schemas out of every assembled prompt and exposes two constant meta-tools (mcp_list / mcp_call) instead

A green pixel-Ork mascot for DSH Web that masks model thinking and output as Waaaaaaagh! until clicked to reveal, plus a random-length input mask.

A Live2D pet companion for the DeepSeek Harness web UI: the Vivi (芊芊) character with petting/feeding, a daily-treat bond economy and mood-driven expressions.

Mobile remote pairing for DSH with QR offers, a loopback Host Gateway, encrypted Relay or Quick Tunnel transport, same-LAN WebRTC Direct, and revocable Device Tokens for the Android client.

Source-filtered HTTP/SSE/WebSocket gateway for using the DSH Web UI behind an authenticated reverse proxy, with loopback trust adaptation, in-app host directory selection, and an allowlisted health endpoint.

File-change diff bar with keep/undo summary, plus dangerous-command approval and red highlighting for bash/pwsh.

Provider-scoped HTTP/HTTPS forward proxy for DeepSeek Harness: configure independent proxy URLs and enable/disable switches per LLM provider, with environment-variable references for proxy credentials and model discovery routing.

Native desktop alerts when dsh needs the human — approvals, questions, plan reviews, turn completion, goals, errors and workflow runs — plus a Settings tab for every option, hot-applied.

Task-completion notifications: desktop alerts via macOS Notification Center and Windows Toast, plus mobile push through Bark, ntfy, ServerChan or any webhook when an agent run goes idle, errors or blocks.

One-shot DSH skill (SKILL.md) generator: capture intent, draft, validate, package and distribute skills from inside a DeepSeek Harness session (skill_new / skill_validate / skill_package / skill_improve_description).

Legacy code modernization workflow (preflight -> assess -> map -> transform) with a Cordis mount plugin, offline Python scripts and smoke tests.

Dual-MediaPlayer daemon ($think loop + $fx one-shots) with volume ducking, mood-aware sounds (smooth/struggle/deep_think triggered by consecutive success/failure streaks and prolonged agent runtime), 15 built-in PCM WAV synthesised from sine/square waveforms, per-tool sound mapping with 51 categorised tools, custom WAV/MP3 drop-in with auto-conversion, and a full settings UI with dark-mode fix.

Auto-switch the DeepSeek route to the vision model on demand: flash main session switches (A), pro keeps deep reasoning and delegates image reading to a vision subagent (B), subagents always switch, with fatal-failure fallback. No manual model switching.

Knowledge base (Vault memory + knowledge graph) for dsh: kb__* tools for deterministic memory search/write, knowledge-graph nodes/edges/subgraph/traversal, document-to-graph ingestion and unified cross-store query (KAL) - no web-search tools.

Linux X11 computer use for DeepSeek Harness: 9 tools (screenshot, move/click/drag/scroll mouse, type, key combos) driven by a zero-dependency Python XTest helper — native-pixel coordinates, per-action verification, optional auto-observation screenshot.