Plugins

Stable, editable PPTX generation for AI agents — semantic IR in, native DrawingML out

Rotates configured LLM API keys after quota, rate-limit, or authentication failures.

Coordinates Codex planning and independent review while the original DSH session implements and tests changes.

CC Switch-style token consumption statistics for the dsh web GUI: per-request usage log, real-consumption hero, request-time-bucketed trend chart, per-model peak/off-peak list pricing, per-project and per-model stats, and account balance.

Adds a VS Code-style workspace file explorer to the dsh web GUI: file tree, editable preview with syntax highlighting, tabs, line numbers, right-click file operations, and inline image preview.

Clean desktop shell for DSH: launch by double-clicking a desktop shortcut like any normal desktop app, live backend monitoring with one-click tray start/restart/stop (progress dialogs), offline auto-reconnect, single instance. Reuses your existing web profile, no restyling of the web UI. Windows + macOS.

Scroll-painting message rail for DeepSeek Harness: a slim right-edge rail with one indicator per user message, scroll-spy follows the reading position, hover unfolds a canvas with full message previews, and clicking jumps to any history message; animates in sync with better-sidebar panels.

Decentralized multi-device fleet: mDNS LAN discovery, key pairing, and SSH direct execution across networks.

Caddy forward_auth administrator login for DeepSeek Harness Web, with Argon2id passwords, revocable sessions, bilingual UI, and a native sidebar sign-out action.

Question-Driven Discovery research workflow for DeepSeek Harness with a QDD Agent Preset, durable Human and Auto runs, and an auditable research panel.

A slim port of Headroom: compresses tool output, cuts up to 20% of context, without affecting the model's context cache or agent performance.

Per-workspace Skill and MCP enablement for DeepSeek Harness: control which skills and MCP servers new sessions load, per project.

Gated multi-agent pipeline for OpenSpec changes — six opx_* tools drive the phase state machine, two agent presets (developer and reviewer) carry implementation and review, and 23 bundled skills define the quality standards they are checked against; full mode runs analyze, implement, then tool, task and dimension-based quality review, while simple mode runs implement and one merged quality review.

Bottom-right quota pill and panel aggregating membership quotas across AI platforms (Kimi Code, DeepSeek, Zhipu Coding Plan, BigModel, Qwen, Scnet, TokenRouter, SupaWriter), auto-syncing API keys from the DSH credentials domain with colored usage bars.

Conversational Grafana operations: inspect live dashboard data across named sources, then make safe, reviewable dashboard changes with approval and version checks.

Local-first persistent memory for DeepSeek Harness: bounded pre-step hot-memory injection, exact and Chinese-bigram BM25 cold recall, six agent tools, approval-gated lease-lock writes with recovery receipts, and read-only governance and trajectory-review candidates.

Enhanced ACP server for DeepSeek Harness: block & reasoning streaming, usage telemetry, model/effort switching, permission presets, session resume/archive, per-session MCP servers, and Zed file/terminal forwarding.

Multi-channel push for DeepSeek Harness: Server酱, PushPlus, Bark, DingTalk, WeCom, Telegram, Feishu, ntfy, custom webhooks and more, configurable from the settings panel and callable by other plugins via the pushNotifier service.

Perlica (Arknights: Endfield) themed tiered sound notifications: plan-ready, task-done, needs-your-input, and error tones; silent for plain chat, system-level playback (works in background), cross-platform (Windows/macOS/Linux), custom TTS sounds.

Academic writing toolkit for DSH agents: paper outlines, title and abstract skeletons, GB/T 7714 / APA / MLA citations, phrasing QA, and a pre-submission checklist.

Biomimetic memory system for DeepSeek Harness: a single SQLite store (node:sqlite, WAL) whose Markdown tree is kept as a read-only mirror; memory tools, frozen-snapshot injection at session start, graded approval gating, on-demand extraction of the current session, near-duplicate merging, an archive and supersede lifecycle, memory metabolism (dream), memory pins, semantic recall over local embeddings, and the /memory command.

Cross-session archive: overview workbench, folded timeline, subagent lineage, full-text search, rule+LLM summaries, ZIP export, live tracking. Native session-page embeds: turn rail, docked right panel (live mode, pinned to original session on switch), rename (official-synced), conclusion digest, health monitoring + persistent header chip (idle / active / tool-wait / stalled). dsh v0.1.2+: fuses with the official TurnNavigatorRail — vector-icon info chips (duration, tool calls, errors, thinking) plus lazy tool distribution inside the official preview card, right-click opens the workbench; the classic piano-key strip is on by default and delegates unloaded-turn jumps to the official auto-load engine; the official rail can be hidden entirely. Settings dialog section with 10 tunable behavior params.

LLM provider that runs the locally installed Claude Code CLI as the model backend, so requests go through an existing Claude subscription instead of a metered API key; native tool calls are bridged over MCP.