All Plugins

Long-term memory injected at session start: preferences/facts/summaries/knowledge in global and per-project scopes, budgeted recall via `agent/pre-step`, durable JSON store.

Native OS notifications for approval and question/plan prompts: the toast names the workspace, click jumps to it, bilingual (zh-CN/zh-TW/en), with chime.

Session-header button that cycles the conversation width (748-1600px), widening the chat column, composer, and user bubbles together.

DSH environment diagnosis, graded repair with one-click rollback, and a runtime self-healing service.

Runtime plugin loading for the Web UI: a watched hot directory installs/updates client-plugin bundles live on every open page, no restart. Includes a right-column subagent dashboard example.

Share any excerpt of a conversation.

Synesthesia Encoder for DSH: a vision model translates images into compact structured spatial text (canvas/elements/percentage coordinates), giving text-only LLMs pixel-level image understanding via the `mm_vision` tool.

Compile SVG paths and keyframe specs into self-contained Lottie JSON animation files.

Update copilot for DeepSeek Harness: one scan covers the dsh core, official bundles, and every profile plugin; explains what changed and how risky each update is, then updates only what you confirm.

Headless Claude Code consultations with advisor, reviewer, and designer roles, returned as reference answers.

Local toolbox for the DSH web GUI: 35 pure-client tools (text, encoding, hashing, extraction, conversion, reference tables) in a sidebar view, plus the /toolbox command and config-driven agent tool exposure.

Move a session to another folder from the Web UI via drag & drop or a menu picker, permanently delete a session with a risk-consent dialog, and AI-rename a session by summarizing the whole conversation (typo-aware). Each action also ships as an agent tool.

Claude Code-style permission rules engine: hard/deny/ask/allow tiers with a hard tier above full access, workspace-scoped rules, wildcard path protection, and a visual staged editor; rules persist in settings.yaml.

Multi-folder workspace: a durable global linked-folders list plus per-session on-the-fly linking (link_folder/unlink_folder), managed from the Web sidebar with a native folder picker.

One-click enter/exit Plan mode for the DSH web input bar, a quick-click shortcut for /plan.

Installation safety gate for DSH plugins: antivirus-style scan of install scripts, permissions, secrets and network callbacks on local directories or npm tarballs, returning a BLOCK/WARN/PASS verdict before "dsh plugin add".

Static pre-install security auditor for plugin bundles: lifecycle scripts, dynamic execution, credential-exfiltration combos, and patch-layer hazards, with zero dependencies and in-memory tar parsing.

Hana-style assistant manager for DSH: visual preset management (cards, yuan personalities, avatar cropping) plus a full Hana memory stack (rolling summaries, layered compilation, SQLite fact store, deep memory).

DSH审批汉化 — approval dialogs translated to Chinese before they render: DeepSeek-powered, host-side, nothing for React to revert.

Character consistency toolkit: personality profile cards, appearance-weight stats, and behavioral-drift detection for long-form fiction.