Plugins

Classifies pending tool calls with Jev (TypeSafe AI's non-generative decision model) on tools/pre-execute — confident high-risk calls are denied, ambiguous ones escalated to approval — and auto-approves clearly-granted reversible calls on approval/request behind argument-evidence gating. Also subclasses the session-reference resolver so snapshots keep Jev-scored messages instead of dropping oldest-first. Degrades to stock behavior on any provider failure; shadow mode with a /jev-stats command; TypeSafe or OpenRouter endpoints; 64 tests.

Twelve official Remotion skills synced from the official upstream (programmatic video with React: animation, audio, captions, 3D, maps, charts, render, Studio), plus a bundled-resource health check. A step-by-step first-run guide (4 steps) now opens inside its settings panel.

Converts session, agent-loop, LLM, and tool lifecycle events into OpenTelemetry GenAI traces and metrics, exported over standard OTLP/HTTP to any compatible backend, with content capture off by default.

Self-contained browser runtime: Playwright (chromium) + OpenCLI as plugin-local dependencies (global reuse fallback), exposes a `browser` service and 9 interactive browser tools.

Multi-provider usage stats framework (v2 adapter contract): persistent capsule plus detail panel; DeepSeek official (interval-bookkeeping daily usage derivation with a peak/valley countdown badge, working even without an official usage endpoint) and OpenCode Go built in; any other data source joins by dropping in a single mjs adapter file, hot-swappable from the settings page, with API keys kept on the host.

Zero-cost access to 6 free large models. No registration, no recharge, 6 free models built-in, multi-key rotation and rate-limit backoff.

Access the dsh web UI over LAN: HTTP/HTTPS/WS forwarding plus TLS (self-signed or custom certificates); adaptive Brotli/gzip compression for HTTP and permessage-deflate for WebSocket; half-open WebSocket probing keeps mobile clients from going stale after backgrounding; launch-token auto-injection lets LAN devices connect without copying the token; DNS-rebinding protection + loopback-only upstream allowlist.

Four-source migration wizard: move Claude Code, Codex, OpenCode and Hermes sessions, memories, skills, instructions and slash commands into DSH (/move wizard with approval gate and idempotent move.json, resumable sessions).

Jev DSH 决策引擎｜面向 Agent Harness 的结构化决策插件。原生支持 DeepSeek Harness，通过 iPolloWork 支持 OpenCode、Codex Harness。

Two-way Codex↔DSH bridge: skills from ~/.codex/skills, session import with workspace attach, live MCP mirroring of mcp_servers, and a Codex-side reverse MCP installer.

Long-term cross-session markdown memory with an LLM-Wiki structure and a SOUL.md persona, injected at session start (by default only after the first user message and only in the active session), plus remember/recall/consolidate/forget workflows, an embedded memory skill, pack/unpack migration tooling, and an idle-time first-person recall nudge that surfaces real memories in a companion voice. Also gives the store observability and upkeep it lacked: a per-file boot-block budget that keeps the index routing table from being truncated, automatic last_access stamping so salience decay actually works, a read-only memory health dashboard (size, freshness, lint-parity checks), a declarative index compiler (pages declare summary:, one command re-lines the index), an interactive memory graph (page links plus shared tags, draggable, wheel zoom), structured queries (tag/type/salience/hot/stale filters), cross-link suggestions for pages that have no relationship yet, and a `checkup` report that ends in a prioritised action list. The boot payload was also cut by ~23% by moving operational detail into the on-demand skill. Its settings section now carries its own navigation mark (a brain half wired to a node cluster, since the shell offers no icon slot to plugins) and a feedback entry that opens this repository. Requires DSH session format v4 (official DeepSeek Harness 0.1.7+): injected messages declare the producer-owned source kind plugin:memory. v0.11 added a bilingual settings panel whose copy and sidebar label follow DSH language setting (中文「记忆」/ English "Memory"); v0.12 added the shared cross-plugin speech floor, a context-sensitive tone section and a weekly growth recap; v0.13 declares its DSH compatibility via engines.dsh (official 0.2.1-rc.5 series; older hosts are refused by the gate), adds a "Review now" button (POST /api/memory/control, action growth-now) that sends one growth recap immediately while still respecting the speech floor, panel accessibility (aria labels, status and alert roles, focus-visible rings), and the public PROACTIVE-PROTOCOL.md. v0.14 adds per-session memory: a composer chip with a dropdown (this session / workspace default), the /memory on|off|status command, and a settings-panel switch all flip the same gate — off means no boot injection, no digest/recall nudges and no last_access stamping for that session (nothing is deleted); disabledWorkspaces lets whole projects default to off, and session choices persist for 7 days. v0.15 adds a Basic soul (quick forging) card: my name / what I call you / baseline persona, saved into a managed block inside SOUL.md (the rest of the file is left untouched) and marks BOOTSTRAP complete; existing chat-forged souls are echoed from the SOUL text, and the boot block now asks the agent to remind the user to forge first when no soul exists yet.

Coding-subscription OAuth for SuperGrok/Grok Build, ChatGPT Plus Codex, Kimi Code and Claude Code, plus an opt-in loopback OpenAI/Anthropic gateway: local login without pasting tokens, AUTH refresh-and-retry, grok-4.6 xhigh, and API-key route coexistence.

Auto mode for DeepSeek Harness (dsh): an Auto entry in the Permissions selector whose approval prompts are answered by OpenGuardrails policy instead of a human — plus the full OGR guard engine underneath. No core changes.

Native interactive answers, editable cards and on-demand UI skills for DSH.

While vibe coding, save an answer you may need later, use Side Chat for a question that suddenly comes up, or open a related conversation for deeper work without losing focus on the current task.

Streaming fold for the DSH web transcript: the newest thinking window opens itself, older process rows fold into one summary, and a finished turn glides back to your prompt, which stays pinned while you read.

MCP management panel for the DSH web UI: per-server status, transport and full tool input schema, with add/edit/enable/disable/remove in global and project scopes, reconnect for global servers, a five-server built-in catalog, and config import from ten other clients with a preview. A project's MCP servers share one connection per (project, serverName) — the first session opens it and the last one closes it — so concurrent sessions reuse a single mcp-client instance; the panel shows how many sessions share it and marks a config change as pending until the connection is rebuilt.

Twenty-one official HyperFrames by HeyGen skills synced from the official upstream (HTML video authoring, animation, keyframes, audio/music-to-video, CLI, registry, slideshow, talking-head recut, website/product/PR-to-video, Studio timeline conventions and more), plus a bundled-resource health check. A step-by-step first-run guide (4 steps) now opens inside its settings panel.

Design workbench in the right sidebar. When the model builds web pages, app screens, WeChat mini programs, posters, slides or emails, each HTML file shows up as a screen on a canvas inside a device frame and refreshes when the file changes; local dev servers are proxied with hot reload intact. Mini program screens get the WeChat capsule in the top-right corner, which turns white over a dark top bar, and the design check flags text and buttons hidden under it. Click an element or drag a region to put its selector, source file and styles into the composer. It can extract a brand design system from your website or project (colors by role, fonts, type scale, radius, shadows, buttons, inputs and cards) and use it for every new design. The model adds a few tweak sliders to each design (spacing, radius, brand color, layout variants) that update all screens live and write back to the stylesheet in one click. A finished design can be turned into React, Vue, Next.js or plain HTML code, with each built screen diffed pixel by pixel against the design. Also has a design tokens panel, fifteen style presets, a style panel (font size, colors, radius, padding and more) that writes back to the HTML or hands the change to the model together with the CSS rule and line behind each property, versions saved before and after each turn with drag-to-compare and restore, export to images, PDF and PPTX (links between screens stay clickable), a LAN QR link for viewing on a phone, link arrows and a click-through demo mode, a multi-size view, in-place text editing, reference-image palettes, and a design check (overflowing, clipped or overlapping text, contrast, tap target size and more). Bundles a ui-design skill and six tools: preview_page opens a preview; check_design measures every screen at real sizes in a hidden local Chrome or Edge (bars covering content, script errors, missing assets, dead links; CSS file and line for contrast and font-size issues; cropped screenshots of serious problems); look_design hands real screenshots to the model; extract_design_system builds a design system from a site or project; handoff_design writes a handoff pack (screenshots, routes, tokens, shared components); compare_design diffs the built local page against the design and marks what differs. Adds a Design mode for new sessions (Standard mode's tools plus the skill, the six tools and a design persona); each part has its own switch on the Plugins page. When DSH is opened from a phone or another computer, local-file designs are bundled into a sandboxed frame so they still show.

VSCode-style editing experience for DeepSeek Harness: a Monaco-based central file editor (tabs, Ctrl+P quick open, status bar) and interactive diff review of agent edit/write results with per-change Keep/Undo, rollback and archiving, persisted across restarts.

Disciplined engineering workflow system for AI coding agents: planning, TDD, auto-fix loops, codebase knowledge graphs, and multi-agent wave execution. Needs codebase-memory-mcp (pip install "codebase-memory-mcp>=0.10.8,<0.11.0"); /scan stops without it.

Free model provider plugin for DSH with 20+ models including Gemini, MiMo, GLM, etc.

Configurable DSH web-surface plugin: wallpaper & frosted-glass themes, accent colors, custom keyboard shortcuts, app-usage panel, history strip, message Markdown — zero shell edits.

Hosts QQ chats as DeepSeek Harness sessions: one QQ conversation maps to one DSH session that survives restarts, per-speaker tool permissions, three-layer memory with nightly consolidation, optional QQ-number binding that ties openids to QQ numbers so memories survive a bot or AppID change (binding is voluntary, never required, and never guessed from nicknames), four-section personas, context compaction, a ten-page sidebar panel, and a setup wizard that installs the Roost kernel and ai-chat plugin. Anyone in a paired QQ group can chat with the bot by default; only the owner gets the full local toolset.