Plugins

GitHub MCP helper panel: shows copyable example prompts at Settings → Plugins → GitHub MCP (random 4 from a 30-example pool), visualizes a public user's repo star/fork/language, and adds the gh_repo_stats and gh_current_user model tools.

Side-ask drawer opened from a completed answer's action row: follow-up questions run in an independent, auto-archived session seeded with the prior conversation text (read-only, capped at 48,000 characters), leaving the main session untouched. The side session inherits the main session's model, switchable inside the drawer, with a context-usage ring.

Local-first personal usage insights in Settings, with 1/7/30-day token heatmaps and a 30-day calendar, token composition, model mix, and skill-call status.

Audit each finished assistant turn with an independent reviewer model and steer the agent to fix failed output, with at most 2 review rounds per turn and SOP-folder standards injected as an extra review dimension.

Pins every request to the native max-effort tier and adds a per-model/per-mode reasoning-depth panel with a 0-20 capability slider, isolated Velocity/Apex profiles, and offline reasoning toolboxes. Distributed as an obfuscated build; commercial use allowed, reverse engineering closed.

Installs a Web-profile helper that diagnoses and writes MCP config so Codex, Cursor, or Claude Code can spawn dsh --profile codex.

Irreversible secret-scrubbing guard: rewrites access keys, bearer tokens, and private key blocks into `[REDACTED:<category>]` placeholders before they reach the session log and the model.

Explicit cross-session work state for DeepSeek Harness: goals, decisions and next steps captured automatically from host events or via a model-visible work_state tool, inspectable with /checkpoint.

Cut token cost in 4 layers without cutting model intelligence: handoff, rtk, headroom, caveman token-saving skills — each also available as a standalone installable plugin.

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.

Vision bridge for text-only DeepSeek: send images (alone or mixed with text) and a fast tiny vision model describes them behind the scenes — the chat keeps the picture, DeepSeek sees only text. Pure plugin: uninstall restores everything.

Windows desktop automation for DeepSeek Harness: accessibility-first observe/act loop with 30 standard tools (element/coordinate targets, auto/a11y/event strategy routing), superseded-observations and no-replay safety semantics, persistent kill switch, RuntimeId/rect-drift stale protection, chat cards and a floating panel (live ops, frame wall, env auto-detect settings), tiled vision describe for low-res models, JSONL audit trail and a pid allowlist. Requires Windows 10+ and Python 3.9+ with uiautomation and pillow (installable from the settings page).

Supervisor-style workflow orchestration over top-level sessions: confirmation-gated batch dispatch, team workstreams, steering running tasks, idle-wait collection and live model-route discovery across 11 task_* tools plus a /tasks slash command.

Aqua glassmorphism theme for the DeepSeek Harness web UI: mica and compatibility modes with adjustable blur and frost, fluid or wallpaper backdrop, background brightness, particle-whale accent, and a master switch that restores the stock UI.

MCP server that searches the Roblox DevForum and official creator docs so AI coding agents can debug Roblox games against real community and engine knowledge.

Per-model capability profiling for DSH: turns local session history into per-model dashboards of session counts, tool usage, error rates, and top error signatures, with time-range filters and multi-model comparison.

Replaces the model button with a Claude Desktop-style model and reasoning-effort switcher, with per-model effort memory, theme-aware styling, smooth slider feel, rounded track, hover highlight, and pixel-dot animation.

Group installed skills and manage MCP servers from a left-panel UI: filter the model skill catalog by enabled groups (union-deduped) and toggle MCP servers independently.

Per-message delete for DeepSeek Harness — a trash icon beside the copy button on every chat message that removes that message from the derived model context (and the visible transcript) via the official surface-replace contract

Delega tareas, reviews y debates a modelos alternativos (DeepSeek, MiniMax, Ollama, etc.) vía el CLI gateway-companion, sin MCP.

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

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.

Three-layer local memory for DeepSeek Harness: L1 snapshot memory (MEMORY.md/USER.md) read on demand through the memory_* tools + L2 searchable knowledge base (facts + SQLite FTS5, Chinese search via sliding-window tokenization) + L3 import from Hermes/Claude Code/Codex/WorkBuddy and from approved Agent Hub documents (memory/global, memory/projects, accepted decisions) with content-hash dedup. v0.2.0 removed every automatic injection: memory enters the context only when the model calls one of the 12 memory_* tools, and data stays on the local drive.

Official DeepSeek platform monitoring inside the provider card: a live balance chip left of the composer model name plus an expandable account-details panel with per-model monthly usage and a daily stacked chart.