Plugins

Read-only Grafana tools that query metrics through the data source proxy: instance health, data source listing, instant and range PromQL queries, current alert state, and provisioned alert rules. Range queries downsample to a point budget; an explicitly supplied step that would exceed it is rejected rather than silently changed, so the model never receives data at a resolution it did not ask for.

Grok Build provider using the official CLI browser login, with dynamic account-visible models, streaming reasoning and tools, plus quota and model-capability settings.

Modellix integration for DSH: schema-driven image, video and audio generation in a split Design workspace, a live LLM model catalog, and native web search and fetch providers through one API key.

Turn your phone into a full-featured camera for dsh sessions (requires the open-source Android companion app — install the plugin and scan the QR code it shows to download the APK): 1. Live viewfinder over LAN or USB, injectable into the chat or savable to a folder. 2. Callable tools let the dsh model take photos, zoom, and switch lenses on demand mid-conversation, so in fully automated workflows the model can actively "see" the physical world. 3. Full zoom/flash, crop, and annotation. 4. Rich settings.

Register models, assist with portraits, and select the Agent model from a secret-free catalog for DeepSeek Harness.

Adds Claude, Gemini, and a local Ollama model to DSH's native model picker, using your existing Claude Code / Antigravity CLI logins instead of a metered API key, with a working reasoning-effort selector for Claude.

dsh web 的 Token 用量热力图：固定近 26 周（周日起始对齐）按天着色、GitHub 风格、深色/浅色自适应；今日/本周/本月/累计四个总量 chip 点击即把明细表锁定到对应时段，可再点选单日；明细按 provider/model 拆分（输入/输出/缓存读/缓存写/占比）。数据全部来自本机会话日志，增量聚合 + 磁盘缓存。

Web interface enhancements for DeepSeek Harness with session rename/fork shortcuts, a searchable model picker with provider filters, mobile layouts, global font scaling, context usage alerts, DeepSeek balance and tariff rates, sent-message navigation, and conversation summaries.

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.

Sidebar session-title icons: an auxiliary model call on the same route as title generation draws a 24x24 monochrome SVG metaphor shown before each session row title, with disk caching.

DSH 模型检测：对任意 pi-ai 提供方，拉取其线上最新模型清单，并用 models.dev 自动富化正确模态/容量/推理后写入该提供方

Unified model routing for DeepSeek Harness: one logical ModelID over multiple providers with first-token failover and cooldown, health-aware candidate ranking, three tiers (tier1/tier2/tier3) auto-selected by purpose, per-candidate reasoning effort, and a settings-page management panel.

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.

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.

Daily cost card for your local LLM gateway: /usage reads gateway_usage.jsonl and itemizes spend per model and per hour, covering official direct, OpenRouter relay, and in-plan metered pools.

Windows computer-use capability for DSH: screenshot → vision model → simulated mouse/keyboard with self-evolving knowledge base. Dual-mode plugin tools + skill-only pwsh fallback.

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

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.

Reasoning-effort tier manager for custom API models plus cross-session preference memory: inline low/medium/high/max toggles inside Settings → Models, with atomic settings writes.

macOS desk pet forked from anneheartrecord/dsh-desk-pet, in a real always-on-top window that covers fullscreen Spaces: the pose follows whatever the local DSH is doing across six states, the right-click menu is a real AppKit one carrying quiet mode and a session list, and seven skins ship with it. Two of the seven are drawn from geometry by a script in the repo rather than generated, so making a skin needs no image model and no API credits; the bundled skill still expands one photo into all eighteen poses on your own image tool and credentials. There is no Electron and nothing to install alongside it: the window is driven through ctypes on the Python that ships with macOS.

Draft polish for the DSH composer: one-click AI polish of the input draft (sparkles button next to send), with optional conversation context and a configurable model channel.

DSH workspace hub: organize workspaces into color-coded folders in the sidebar (three-level drag reorder for folders/workspaces/sessions, inline edit, one-click expand/collapse, dual-channel search) with per-workspace and per-session token usage and cost stats from real session logs (official DeepSeek peak/off-peak pricing for any deepseek model, three spend calibers, hover detail cards, overview panel) plus OpenCode Go plan usage; data persists to host disk and refreshes live every 30 s.

Ship a project to Cloudflare and publish your plugin to npm — the first deploy needs no cloud account, and credentials never reach the model.