Plugins

Tool-call discipline for DeepSeek Harness: injects a static behavior-constraint prompt section, drops the parallel pool to 1 after a tool failure (restoring after 3 consecutive successes), nudges the model to stop retrying after repeated failures, verifies writes with .bak rollback, gates high-risk commands, and tracks compliance stats via /behavior-status.

Cache-stable progressive tool discovery: a fixed tool_search and tool_dispatch surface on every request, in-memory catalog search, nested dispatch through the Harness pipeline, and a byte-stable native tool list across discovery.

Kiro model provider with Builder ID, Identity Center, Google, GitHub and credential-import sign-in, automatic token and profile refresh, account usage, live model discovery, selectable reasoning efforts, streaming tool calls, provider stop-reason and context-overflow handling, and token accounting that uses Kiro's exact counters when it sends them and otherwise scales the context-usage percentage it does send by the model's advertised window.

A self-healing layer for tool calls: missing params, wrong fields and out-of-range paths are fixed before they reach the model. Measured visible error rate fell from 7.95% to 2.20%.

Per-round thinking-level (reasoning_effort) control for DeepSeek Harness: pick Auto and it schedules low/high/max from the recent tool-call history, or fix a wire level (off/on/minimal/low/medium/high/xhigh/max) manually, with custom wire mapping, a model-aware capability guard, and context-window presets (64K–1M); its per-model capability card pairs with a separate plugin, [dsh-llm-openai-completions](https://github.com/drscrewdriver/dsh-llm-openai-completions) (installable from dsh-market), so custom OpenAI-compatible gateways (vLLM / LM Studio / self-hosted) can try reasoning — the card writes llm-pi-ai capabilities, the adapter drives the wire (compat.thinkingFormat), and this plugin auto-maintains the takeover list.

A visible Chrome window per DSH session: 16 chrome_* tools (open/status/close/navigate/tabs/snapshot/screenshot/click/click_at/fill/type/press_key/hover/scroll/evaluate/wait), a Chrome tab in the Web GUI with a live screencast view (screenshot-heartbeat fallback for idle pages), tab management, window controls and a screenshot history.

SSH remote workspace — run bash, file tools, glob and grep on a remote machine over plain sshd (exec + SFTP), zero remote install, purely additive.

Live security beacon for DSH that follows tool activity. Click to view call statistics, risk provenance chains and blocked actions, with read-only task restrictions and tool metadata change detection.

AI-driven drawio: four agent tools (validate, render to SVG/PNG, edit, template) plus a sidebar live board — zero-dependency mxfile-to-SVG preview, embedded diagrams.net editor with save bridge, and auto-open whenever the agent draws.

Wakes the main agent after any DSH restart so interrupted work resumes automatically — adds a restart tool and an optional canary that validates the boot and aborts with an alert before a broken restart.

Browse and install DSH plugins without leaving the harness: a /store command, a Settings → Plugins tab, two agent-callable tools and a bundled skill, with an approval gate that lists the detected risk flags before anything installs.

Dead-code detection for AI-generated codebases: graphlint builds a dependency graph, finds code unreachable from any entry point to enable codebase cleanup and functional‑effectiveness understanding, and exposes graphlint_query / graphlint_build / graphlint_config tools plus a graphlint skill to DSH agents.

Playwright MCP browser control for AI agents: drive a real, visible Chrome (navigate/click/type/snapshot + ~80 browser_* tools), with a live screenshot panel embedded in the GUI that refreshes after every action.

ChatGPT Codex subscription chat: official OAuth, a Sol/Terra/Luna catalog with Fast rows, live usage limits, and optional search and view_image tools.

Codex-style tool call folding, collapsing multiple tool calls into a single line.

Piano-key in-conversation navigation for the Web UI: one key per user message with hover ladder, message-preview tooltip, and active-message highlight; click to smooth-scroll.

DSH Director Toolkit is a DeepSeek Harness plugin for 3D artists, technical designers, and creative coders. Paste a half-formed idea, a reference note, or a portfolio caption and get a compact direction pack for Blender, Three.js, Houdini, or C4D.

把你的任何想法，变成每个平台原生的宣发内容 | Turn any idea into platform-native publicity

DSH 真实浏览器插件：通过 Kimi WebBridge 让 Agent 操作用户已登录的浏览器，并提供 13 个 webbridge_* 工具。 / Let DSH Agents use your signed-in browser through thirteen Kimi WebBridge tools.

TencentDB Agent Memory integration with conversation capture, structured memory extraction, automatic recall, and memory and conversation search tools.

Bridge dsh session status to the cc-pet desktop pet bubble: thinking, tool calls, and completion in real time.

Rings your phone over CallKit: `call_me` and `text_me` tools, plus optional turn-end and approval calls whose spoken answer is transcribed back into the session.

Adversarial checkup → fix → review loop toolset.

Recurring loops: `/loop` command + loop tool + activity status bar.