All Plugins

Image-to-text input for the Web UI: paste or drag an image and it is transcribed into structured text and sent, giving text-only LLMs image-input takeover (OpenAI-compatible vision API).

Window-like controls for every Web UI modal: drag by title bar, eight-way resize, pin against outside clicks, maximize to the full viewport, removable backdrop blur, and per-dialog persistent state.

Wallpaper skin for the DSH Web UI: presets, image URL or upload, and an opacity slider that fades the interface to reveal the wallpaper.

Aseprite-style pixel art studio: the AI draws sprites stroke by stroke with selections, layers, animation frames, gradients, symmetry and reference layers, each step rendered live as ANSI terminal frames.

Export complete Web Sessions to local Markdown or self-contained HTML, with stable rendered previews, default redaction, and opt-in bounded tool-call details.

Chain-of-thought leakage linter: zero-dependency CLI that finds AI-session residue in docs and comments (dead design citations, PR vantage, change narration, review choreography), shipping the cot-trim fixing skill as the installable bundle.

Ingestion-time tool-output curation: keeps error and warning lines plus head and tail, spills the full text to disk with a pointer the model can read back; covers every text tool, small results pass through untouched.

Update checker (npm edition): a settings page comparing local and latest versions of @deepseek-ai/dsh and every installed plugin, with a red-dot nav reminder and ready-made update commands.

Restore archived sessions to their original workspace from the Web GUI sidebar.

Voice input for the web UI: a mic button in the composer that transcribes speech into the draft via the Web Speech API, with an optional auto-send toggle.

One-command bundle of the three AgentFrame plugins: memory-director, compaction, and aura-scheduler together.

Open registered workspaces from the Web UI in a detected or configured local editor, terminal, or file manager, with a remembered per-browser preference.

Human-in-the-loop tools (`human_task` / `human_task_ready_check`): pause the agent until the user performs a real-world action or returns an observation (GUI operation, game testing, visual verification, hardware checks), gated by session consent and an AFK presence check, returning a structured JSON result via a web task dialog.

Real PTY terminal panel for the DSH Web UI: host half spawns shells with node-pty (cmd.exe default on Windows), rendered in the browser with xterm.js; multi-tab sessions, dock/floating window, clipboard support.

Compaction backend replacing LLM summarization with a deterministic semantic extractor (keeps code/paths/commands, drops chatter) plus 28.4x KV-compression accounting.

Settings-page usage dashboard: per-provider/model token summary across all sessions, with today/7-day/30-day CSS-bar trends and a cache-hit rate.

Plugin value auditor: pre-install review (source scan + LLM judge) and post-install audit of installed bundles, with model-switch re-audit reminders.

Email reminders from your DSH agent when you're away: fires at goal completion, blockage, before asking the user a decision, and at long-task milestones via a bundled zero-dependency Node SMTP sender.

Injects allowlisted GitHub Actions and GitLab CI run metadata into agent context without reading logs, credentials, or provider APIs.

Cross-session memory for the model: full-text search all past sessions (SQLite FTS5 via ctx.sessionQuery) and bring the strongest matching excerpts back into the current context.