Plugin

Reminder bubbles beside the input for DeepSeek Harness: any plugin or AI can push reminders (text/link) with chat-style stacking, drag-resize, AI summary, visual customization and random outfit presets. A static profile plugin available in every preset without disappearing on restart.

Task Runner mode for DeepSeek Harness: the main agent decomposes large tasks into independent subtasks, dispatches them to subagents (default local model) in fresh short contexts, and synthesizes results; concurrency and worker/orchestrator models are configurable in the settings panel.

Turns a product or UI request into an implementation-ready design spec with /ui-workflow and /ui-rerun. Analysts run through a read-only ui_analyst tool, and the lead agent writes docs/ui-workflow reports.

Multi-agent isolated debate for DeepSeek Harness: debaters of different temperaments research independently (no herding), then cross-examine, then judges converge to a conclusion. Runs as a background job with per-agent progress, token accounting, wave-parallel execution, and session-referenced resume.

Plan-and-execute orchestration over ReactLoopAgent — turns a goal into reviewable steps with a web UI plan card.

Captures every plan the agent presents through exit_plan_mode as markdown under <workspace>/.dsh/plans, opens a review window, and keeps a Plans history tab recording the outcome of each plan.

Context compaction / headroom for DeepSeek Harness — compress the live context so the prompt stays small without losing the state that matters (layer 3).

Session context handoff for DeepSeek Harness — stop re-reading and re-deriving context every session. A single skill (layer ①) that keeps the next session warm.

dsh port of the shared handoff kit: handoff and task-id-bootstrap skills plus host-side automation — baseline state injection, per-turn snapshots with an Auto Log trail, task=<id> routing, continuation re-injection, a compaction guard with clear-required alerts, and read-only subagent handling — all writing the same .agents/state/ as the Codex, Claude, and pi editions for one-repo multi-agent handoff.

Voice control for the DSH web composer: push-to-talk speech-to-text into the input box (with optional auto-send), spoken playback of assistant replies via the Web Speech API, right-click settings popover, and a global Ctrl+M hotkey.

Vision bridge for text-only DeepSeek models: transcribes attached images with deepseek-v4-flash-vision-exp before they reach deepseek-v4-pro, with no third-party dependencies.

Apple on-device Vision tools for text-only dsh models: local OCR (zh-Hans + 30 langs), image classification, face detection, document layout, and a combined describe — 100% offline, no API key, tall-screenshot slicing.

Resident-index grep for DeepSeek Harness that shadows the built-in grep/glob tools under the same names: repeated content searches hit an in-memory index ranked by access/modification frecency, and glob serves the built-in ripgrep semantics when available, falling back to the index otherwise.

Sidebar disk browser for DeepSeek Harness - browse any folder on the server (including hidden ones) with text preview, streaming download and upload (multi-select / drag-and-drop, overwrite confirm), responsive on desktop and mobile.

Dalla chat alla tela e all'opera: guida ComfyUI come IDE visuale dei workflow in DSH. Incorpora ComfyUI (locale o cloud) come tela a schermo diviso in DSH Web: l'agente scrive prompt e script nella chat, li applica dal vivo e produce immagini, musica, video e 3D. Operazioni: comporre pipeline, leggere/scrivere workflow, modificare nodi, cablare collegamenti, eseguire, regolare e correggere. Produzione: sweep di parametri in batch (batch_run) e recupero automatico degli output nella chat (get_outputs). Manutenzione: avvio e aggiornamento con un clic di ComfyUI, core e nodi personalizzati. Questo pacchetto è il plugin lato DSH e include il nodo ponte lato ComfyUI.

Folds the tool-definition prompt surface when many MCP servers are installed: a static KV-cache-stable catalog plus BM25/bge-m3 hybrid tools_search and batch tools_schema expansion, so hundreds of tools stay discoverable without spending their full schemas every turn.

Deterministic Reasoning Engine (DRE) for dsh: dre__* tools for knowledge verification (three-stage discrimination), deterministic cognition loops, constraint solving, mental models and synapse memory - strengthens information certainty.

Adds a structured TextIn xParse tool and document parsing skill to DeepSeek Harness, supporting document parsing, cached-content navigation and durable multi-document tasks, with AppKey or Device OAuth authentication, paid-operation approval and bundled cross-platform CLI binaries.

Drag-and-drop enhancer for the composer: drop .md/.txt/.markdown to inline small files into the draft or save large ones to .dsh-drop with @-references (Shift forces inline), and drop SKILL.md packages to validate frontmatter and install them to project/user skill roots with one click - effective immediately via the skill watcher.

Codegraph CLI as eight code-intelligence tools for DSH — symbol search, callers/callees, impact analysis, codebase exploration, symbol/file reading, index status and sync.

Cloudflare D1 tools for agents: d1_list/query/exec/schema/stats/health over the D1 HTTP API, read-only by default with a SQLite-accurate lexical guard, LIMIT row cap, CSV/JSON query output and an approval-gated write path.

Codex-shaped coding tools and agent presets for GPT models on DeepSeek Harness: exec_command, write_stdin, apply_patch and view_image, plus OpenAI Chat Completions and Responses API routes, bridged to DSH-native plan, ask, approval and compaction. Long-running commands become DSH background jobs with bounded head/tail output readable through job_output, and each subagent type can be pinned to its own preset, provider, model and reasoning effort.

Record terminal/tool output as asciinema v2 (.cast), replay with an offline embedded player, and export HTML.

Native WCAG accessibility scanner: runs axe-core over local HTML files / build output / URLs and reports violations (rule id, impact, WCAG 2.1 mapping, element targeting, fix suggestions) as Markdown/HTML/JSON. Read-only, CI-able.