Plugins

Configurable send and newline keys, a composer context menu with three sources (leave it to DSH and other plugins / browser menu / plugin-styled custom menu), a quick-command panel with categorized prompt lists where each prompt can append on every send or only on the first message of a session, a create-and-move row at the bottom of each category, a prompt optimizer that rewrites the draft with a separate model call, settings-panel size memory, and automatic x-opencode-session header injection for OpenCode routes. Prompt lists live in a global ~/.dsh/quick-prompts.json that is independent of the session and the project.

Honcho memory plugin by Plastic Labs: injects the user profile, session summary and relevant conclusions at session start, uploads each turn to Honcho in the background with secrets redacted, and adds honcho_search / honcho_chat / honcho_remember tools plus a /honcho status command; configured through the ~/.honcho/config.json shared with the other Honcho integrations, against hosted honcho.dev or a self-hosted instance.

Agent discipline guard for DeepSeek Harness: four gates enforced at the harness boundary — loop circuit-breaker, token-cost fuse, route-switch warning, plan approval — where prompt-level reminders can't reach, so an agent can no longer burn a weekly quota in minutes; one-click 🛡 chip, hot-reloadable thresholds, and presets from invisible-but-armored to warn-only.

Read-only insight panel for one profile: five views over the same data — config layers, plugin tree, services, tool names and models — each entry showing which layer inserted or disabled it and whether it is running.

Adds subagent_route and subagent_fork_route delegation tools where the model itself picks the provider/model route for each child; the deployment only sets the spawn/fork backend, background policy and allowedProviders allowlist, while continuable children and background jobs reuse the official send_message / job_output tools.

Full-pipeline Chinese translation for the dsh web GUI: live translation of the model reasoning as it streams, in-place Chinese below each English reply, and one-line Chinese summaries for tool outputs and tool-call glosses — a standalone provider request that never enters the session transcript.

A self-evolving plugin for DeepSeek Harness: it observes how the agent runs, proposes improvements to its own assets via the LLM, validates each proposal inside a sandboxed trial agent, and applies only verified mutations — with a versioned ledger and automatic rollback on regression.

Visual development studio for DSH WebUI plugins with isolated Git worktrees, live official-WebUI previews, source editing, patch inspection, builds, and validation.

Local image, voice, music and SFX generation plus transcription, with pinned identity: characters, animals, objects and actor voices are defined once and reused on every later call, degenerate output (a near-flat image, silent audio) is rejected instead of returned as success, and a generated line can be read back as text so a clone that swallowed its ending becomes visible. The engines unload when idle, and image generation and transcription can each be pointed at an OpenAI-shaped API instead of the local Vulkan backend.

Interval heartbeat that wakes each root agent itself (followup injection) to proactively report progress, risks or blockers: busy-safe queuing, no stacking, auto-pauses when no human replies, re-arms on the next user message.

Turns the user into an RPG protagonist: after each finished user turn a random "adventure" may trigger, drawn from 700+ events across 7 themed pools (sci-fi, fantasy, ancient, anime, novels, wuxia, urban), growing six persistent attributes (strength, intelligence, agility, charisma, luck, vitality) with XP, levels and attribute-weighted story branches, configured via a settings-page UI.

A structured multi-panelist review workflow for the DeepSeek Harness: N panelists score in isolated subagents, blind to each other; a chair reconciles disagreement by anchor match then Δ-level adjudication; an independent critic audits the process. Works for design, code, paper or project review.

Ask-before-act approval for every edit and every bash command: a red/green line diff before a file is touched, a description+command panel before a command runs — approve once or reject, each gate with its own master switch in Settings → General.

Lets sandboxed agents reach the web through your local proxy: net_fetch fetches pages, net_proxy_status reports proxy status.

Feynman learning-mode plugin: teach → teach-back → judge → re-explain loop rendered as rich HTML lesson cards (mermaid diagrams + shiki code highlighting).

让 DeepSeek Harness 的第三方 API 支持低、中、高等推理强度，并可为每次子 Agent 调用选择模型｜Add Low, Medium, High, and other reasoning levels to third-party APIs, with model selection for each subagent call

Niubash-only shell executor and Bash-dialect teaching for DeepSeek Harness (dsh 0.2.0-rc.2, and the 0.1.7-rc.x line it shares its shell seam with): every ctx.shell execution runs as `niu -c`, PowerShell/cmd/WSL/nu handoffs are refused, PowerShell habits a

Brings models from the Qoder app already signed in on this machine into DeepSeek Harness, with no token to configure, and shows each model rate and off-peak window on its settings card.

DSH plugin that registers the ai-eight-honors-eight-shames skill: eight checkable working rules for coding agents (verify before calling, confirm ambiguity, cite evidence, reuse before creating, test before claiming done, follow local conventions, separate fact from inference, keep changes reversible) plus a ninth rule that logs each user request and the change made in report files at the workspace root.

Tree view of a DSH conversation: editing an old message forks the thread, every version lives in one tree while the sidebar keeps a single entry, branches can be renamed, and a branch can be promoted to a session of its own.

DeepSeek Harness (DSH) 推理等级自动选择插件：由 Jev System One 模型判断每条消息值多少思考量，按模型声明的等级自动推导档位，上下文信封让「继续」这类追问继承话题深度，低置信度向上取，任何失败都静默沿用原等级。 | Jev-driven reasoning effort per message: per-model ladders derived from what each model advertises, a fixed-size context envelope so follow-ups inherit topic depth, ties break upward, silent fallback on every failure path.

TraceScope DeepSeek Harness plugin 鈥?embedded React Slot UI + same-origin APIs

A native reasoning-effort control for the composer: a blue-to-violet tier bar with a starfield and a sheen sweep. It owns the model seat and drives the official model-directories service, so the ladder comes from each model's own reasoning declaration and no other plugin is required.