Plugins

MCP marketplace and management panel in the Web sidebar: one-click official templates (Apifox public/private, Apipost, MasterGo, Pixso), paste raw mcpServers JSON, and enable, edit or delete your services with hot reload.

Background notification plugin: desktop notification, with a tab-title fallback, when an approval prompt or an ask-user-question card appears while the page is in a background tab. The host queues approval and question events behind a same-origin endpoint that the client polls every 3 seconds; clicking the notification focuses the page, and the tab title is restored once the page becomes visible.

Self-evolution actuator: consumes problem tickets mined from session logs, synthesizes skill candidates (zero-code tiers by default) behind an eval gate with hold-out canaries, then promotes to project .dsh/skills with human confirm and deterministic rollback.

GLM (Zhipu bigmodel) web search provider - routes ctx.web search through Zhipu's Anthropic-compatible endpoint with the native web_search server tool, billing your existing GLM quota or Coding Plan instead of the DeepSeek platform. Includes a translation layer for Zhipu's non-standard tool_result response layout.

Configurable web search hub for the built-in web_search tool: switch the active entry between DeepSeek official native search and Zhipu GLM web_search, with entry and credential management on a Settings page tab.

Attach tables and documents (xlsx, csv, pdf, zip…) to the DSH composer via paste or drag-and-drop: files are saved into the session workspace and an @reference is inserted.

Share the DSH workspace over the local network: phones, tablets and other computers browse, download and upload files via browser with no DSH login. Token gate, path boundary, read-only mode and rate limit. Zero-dependency (node:http).

Text-to-image and image-to-image generation via OpenRouter's unified Image API: configurable model aliases with parameters gated against the live model capability listing, reference-image inputs, a settings card, and inline chat display of results.

Install and call external Agent CLIs (Codex, Claude Code) from DSH without touching the system install. Each CLI gets its own Provider, model, reasoning effort and permission preset, callable directly or as a native subagent.

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.

Image generation workbench and agent tool for DSH: one tool (ark9_generate_image) paints text-to-image and image-to-image via any OpenAI-compatible API. Channels are entirely user-configured - no bundled endpoint, you bring your own baseURL, key and model name (manual input supported). Agent-initiated generations are approval-gated by default: requests queue in the floating panel and nothing bills until you approve; approval is non-blocking (the agent replies "awaiting your approval" immediately, and results, denials or timeouts are injected back so the agent reports them in the next turn). Floating glass workbench with five tabs (Generate / Approvals / Prompts / History / About), aspect-ratio grid with quality-budget + 16px-alignment sizing, transparent background, batch up to 10 images as aggregated sub-tasks, prompt library with custom JSON sources fetched through a host proxy, persistent generation logs with one-click retry, multi-channel aggregation with per-channel model fetching, bilingual UI (zh/en), stroke-SVG icon set, config import/export. Registers as a Better Sidebar tab when dsh-better-sidebar is installed; stacks above the dsh-cua FAB when both are present.

Memory consolidation tuning for dsh-mneme (autoDream enabled, schema-max output budget, deepseek-chat route) plus the llm-deepseek reasoning-effort fix, an MCP bridge to the auditable seed-society agent runtime, and six yogacara seed skills.

Session health-check: mechanically mines session logs into structured problem tickets (retry loops, tool-error clusters, interrupted turns, token waste) over the official session-query seam; works standalone.

Neutralize tool calls with invalid JSON arguments on the wire so one malformed model generation cannot brick a session against strict OpenAI-compatible servers.

Launches a fresh, continuable parallel session from the composer command menu (/side-chat) while the main session keeps running.

Command Code LLM provider for DSH Desktop: registers the commandcode route with a live model catalog, configurable request and stream-idle timeouts, multi-account rotation on 429/401, plan-aware model filtering, an OAuth login flow and a bilingual usage and billing panel.

Floating GPU monitor for the DSH Web UI: a compact, draggable strip with one row per discrete GPU (exact name, utilization, VRAM, temperature, power draw) from nvidia-smi, stays visible over side panels and side cards, with a top-VRAM-process list when the driver reports it; degrades to an n/a pill on machines without an NVIDIA driver.

A floating stock ticker for DeepSeek Harness: real-time quotes for Nikkei 225 and TOPIX ETF out of the box, plus worldwide markets via Yahoo Finance — Japan (.T), US, Hong Kong (.HK), China (.SS/.SZ) and any other symbol — with a customizable watchlist, display aliases and 16 UI languages.

Adds a visible vertical scrollbar to the DSH Web settings navigation when its sections exceed the viewport.

Browse and govern the skill library from a floating-ball panel with three tabs — skills, call ledger and quick start. You choose the skill root yourself through a native directory chooser (defaults to ~/.dsh/skills, no path is shipped with the plugin); skills are grouped into two levels of categories, with manual, keyword-based and AI grouping available and a tree or flat view toggle, and grouping is purely visual so no skill file is ever moved. Descriptions are read from each SKILL.md frontmatter, search filters by skill name, description or original text, and a card opens the full SKILL.md. Skills can be switched on and off per card, per category or for the whole library — the toggle rewrites disable-model-invocation in that SKILL.md and writes a SKILL.md.bak-toggle-<timestamp> backup before saving, rolling back if the write fails; disabled cards grey out until restored. The call ledger separates automatic from manual entries, records skill successes and failures by listening to tools/result events, and reports call counts, success rate, trend and a ranking, reusing an existing ledger file found in the library. Hot reload picks up skill edits without a restart. The DSH settings page gains a floating-ball section that shows or hides the three balls, offers one-click restore of a ball dragged off-screen, and picks the shared 130-skin catalogue for all three balls.

Shows a 0-100 conversation coherence badge and commentary by running parallel contradiction analysis on the live DSH session, with a manual trigger and interval-based auto-analysis (on by default, editable per session or globally).

Adds lightweight selected-text references to DSH assistant replies: selections stay outside the editor as removable draft contexts, remain marked beside the source, and render as hoverable annotations after submission.

Conversation-level multi-agent workbench for editable task planning, real child-session observation, plan-versus-runtime comparison, and evidence-backed recovery previews; tested with DSH 0.1.1-rc.2.

Hard-stops further tool calls after a configurable per-session budget is reached.