Plugins

LLM provider adapter that routes model calls through any ACP (Agent Client Protocol) server — Claude Code, Codex, Gemini CLI, Devin and more — with a registry browser, per-server settings UI, lazy authentication, and dynamic model discovery.

Configurable image recognition for text-only DSH models: image messages are first transcribed by an OpenAI-compatible vision model (Base URL, model ID and API key set in a Settings section) and then passed to the main model as text, while image-input support is advertised. The API key auth scheme is selectable — OpenAI, Anthropic, Gemini or Azure style request headers — and a missing key is reported before any request is sent.

Routes the DSH web_search tool through Ollama's web search API, reusing OLLAMA_API_KEY. No DeepSeek official key needed.

Drag-and-drop file upload into the conversation composer, token usage pill with quota tracking, and session archive management — a three-in-one daily-driver addon.

DSH Desktop enhancement plugin: task-execution discipline plus a real relationship, per session. Discipline: adaptive protocol tiers (short for chat / full for tasks / lean for reasoning models), intent routing across Q&A, lookup, discussion, diagnosis and execution (diagnosis never fixes unasked), evidence recency (verify timestamps and causality before citing logs or old errors), real tool-result verification (failed or unknown results are never reported as done), self-healing on repeated failures with a cross-session reflection loop, compaction awareness that re-anchors state after the host condenses history, and document-capability awareness (probe for document tools and constrain accordingly: with tools, read before you write and read back before claiming done; without them, state the boundary instead of hand-parsing binary office files). Persona: distill named characters from chat logs, novels, scripts and character-setting documents, with tone, catchphrases and reply length anchored to real material statistics; long-term memory with automatic expiry for time-bound facts, corrections captured as style rules, approved replies pinned as corpus, two-way feedback that converges with use, memory star map, and persona card export/import. Constraints are injected only when relevant, so idle chat pays no extra tokens.

DeepSeek Harness plugin that aggressively saves tokens without affecting task quality: lossless head/tail truncation of tool results (default), grep-result folding, pressure-triggered dsh-compaction-basic delegation, and an LLM-summary CompactionEngine subclass for the aggressive mode. Saves 97.6% of input tokens on an 8-scenario synthetic suite, with all reductions routed through dsh event flow so model-visible = logged stays intact.

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.

Kimi WebBridge host plugin for DeepSeek Harness: model tools that drive the user's REAL browser (navigate, snapshot, click, fill, evaluate, screenshot, network inspection, tab management) through the local kimi-webbridge daemon

Real-time hot topics panel for the DSH web GUI: AI news and engineering news, each item with a distilled summary and the source link, shown from a sidebar entry with three views, keyword/source filters, read-state marking and hotkeys.

DeepSeek Harness appearance theme pack — NEXUS / COMIKET / IRONCORE, three themed editions (palettes from keyshub.top / isolo-news) with wallpapers, a settings row and a sidebar quick switcher

Maintainer and developer PR board for the DSH sidebar: a five-state review queue (waiting on me / waiting on author / ready to merge / merged / inbox), a three-column issue board, and a global view of the PRs you authored (my move / waiting on others / merged), with CI rollup badges, an inactivity filter, and one click per card to open or start the matching review conversation.

Local semantic code search for DeepSeek Harness: fragment-level symbol-aware indexing, offline lexical embeddings or an OpenAI-compatible endpoint, and hybrid vector + BM25 retrieval fused with RRF - three dsh tools plus a sema CLI.

Context manager for DeepSeek Harness: auto-summarizes every turn into priority-sorted records, injects them plus pinned cross-session notes and custom text into each model request, and folds any-size real conversation ranges into summaries to save tokens. Persistent and restart-safe. NOTE: manual multi-step install — copy the three package folders into profiles/node_modules and add the provided cordis.patch.yml rows, then restart DSH; not a standard one-command install.

iPhone-style agent phone: dual-panel calls & SMS, RCS group chat with trust gates, cross-device agent messaging via the registry inbox bridge, L0–L4 trust badges and evidence audit. Experimental: trust summaries are not a security guarantee, and SMS/signalling is relayed through the operator's inbox (visible to them); E2E encryption is planned.

Read-only Sentry tools: project listing, issue search at organization or project scope, single issue detail, and the latest or a specific event with a trimmed stacktrace. Local variables, request headers and bodies, query strings, packages and secret-looking tags are removed before the event reaches the model, and oversized events degrade through source context, breadcrumbs and frames rather than failing.

Writing bridge to the open-source QingAgent client: the agent drafts and revises documents through qing_ prefixed host tools, typeset on a rice-paper panel with mermaid, drawio, tables and KaTeX; edits stage as reviewable diffs and land only on commit, and it requires the QingAgent desktop app on the same machine.

Listen to Ximalaya podcasts and audiobooks inside the DSH web UI: search albums, browse paginated tracks, and play through a now-playing bar (prev/play/next, seek, volume, rate). After QR login the "Mine" page lists your liked tracks (click to play), subscribed albums with latest-episode hints, and followed anchors with their public albums; the host relays audio streams with Range support and registers an `ximalaya_play` tool so the agent can search and play on request.

Read-only Grafana tools that query metrics through the data source proxy: instance health, data source listing, instant and range PromQL queries, current alert state, and provisioned alert rules. Range queries downsample to a point budget; an explicitly supplied step that would exceed it is rejected rather than silently changed, so the model never receives data at a resolution it did not ask for.

Electrical and electronics calculation plugin for DeepSeek Harness: every computation runs through dedicated tools on self-describing complex value objects in SI base units, with an isolated calculation agent preset and a records panel that archives every solve on disk.

Inspect and simulate DSH context consumption with trajectory and inventory views, and create, inject, import, or safely repair session messages through the integrated Message Forge.

Modellix integration for DSH: schema-driven image, video and audio generation in a split Design workspace, a live LLM model catalog, and native web search and fetch providers through one API key.

Add a theme-adjustment panel under Appearance to customize accent, background, foreground, contrast and gradient, applied live through theme token overrides.

One-click launcher for DeepSeek Harness: detects whether the backend is running, starts dsh web if needed, waits until ready, then opens the main page in a new Chrome window. Ships a cross-platform CLI (dsh-launcher start / open / status / make-shortcut) and the harness_launch agent tool.

Dual-engine screen capture for DSH: inside the SSiD desktop shell, a global hotkey or tray opens a fullscreen box-select overlay (all monitors, per-display pixel-perfect frames) with in-place red-box annotation and a WeChat-style toolbar; in plain DSH (browser), the composer camera button captures the display via getDisplayMedia and reuses the same single-phase box-select + annotation overlay in-page. The cropped image lands in the current conversation composer through the official attachment intake.