Plugins

Card-style plugin manager in Settings: enable/disable each plugin through the profile patch layer, install-source details, npm update check with one-click update, uninstall, search, and load-error badges.

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.

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.

AI-driven presentation workflow packaged as a dsh skill: generates editable PPTX decks and SVG snapshots from PDF, DOCX, URLs or Markdown, fills native PPTX templates, and enhances finished presentations.

Native-feel DSH attachments: official PNG/JPEG/WebP/GIF thumbs plus 64px cards for other files via drag, paste, or paperclip; non-images land in .dsh-uploads and sent cards sit on the user bubble.

Optimized fork of dsh-image-gen with batch generation (count), gallery pagination, lazy loading, fetch retry/timeout, and 7 providers: Gemini/OpenAI/Seedream/DashScope/Agnes/GLM-Image/Stability AI.

Manage global AGENTS.md in DSH Web with Markdown preview, reusable templates, version history, import/export, failed-import rollback, and revision-conflict protection.

Spritely — a floating work-state mascot for the dsh web UI: it animates with the agent's live activity, tracks the cursor, and offers switchable characters, draggable placement, and customizable backgrounds.

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.

TickTick (滴答清单) daily task dispatcher: an interval timer pulls due tasks from a chosen list into a Markdown task file and notifies only when the task set changes (WeChat via ClawBot / flomo / macOS); it can also auto-execute each task in its own headless DSH session under a configurable timeout, optionally gated to DeepSeek's off-peak hours so peak-time work queues to the next off-peak window instead of starting, plus a settings panel for the deferred write-back queue and dispatcher_status / dispatcher_config / dispatcher_run / dispatcher_report tools.

Learns what you leave unsaid in your prompts from messy turns and your own corrections, and injects the learned directives into the system prompt of every new conversation; the directives are editable in Settings and a composer button rewrites the current draft with them.

Read-only insight panel for one profile: five views over the same data — config layers, plugin tree, services, tool names and models — each entry showing which layer inserted or disabled it and whether it is running.

Adds subagent_route and subagent_fork_route delegation tools where the model itself picks the provider/model route for each child; the deployment only sets the spawn/fork backend, background policy and allowedProviders allowlist, while continuable children and background jobs reuse the official send_message / job_output tools.

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.

Separate slash-command group in the Web UI composer: /steer injects text on the agent's next step without interrupting the turn, /new starts a blank session, /skill and /docs wrap /steer with post-turn skill or docs tasks, and custom /steer aliases are configurable in Settings.

Task control for DeepSeek Harness: one-click emergency stop and force-termination of stuck downloads and tool calls, download progress, stuck detection, pwsh activity monitoring, and append-condition / pause / resume with invisible recovery.

Durable DAG workflows for DeepSeek Harness with Agent authoring tools, SQLite persistence, resumable runs, and a visual Canvas Studio.

FormatForge for DeepSeek Harness: forge any file format (pdf/docx/xlsx/pptx/eml/toml/...) into AI-readable structured data. Thin bundle that spawns the local Python CLI (python -m formatforge) and returns protocol JSON; enhancement is delegated to the cur

Skill studio for DeepSeek Harness: visualize every agent skill (name, description, source, nested flag, model/user invocation), view and edit the full SKILL.md body, toggle model/user invocation, and mine DSH session logs to extract reusable personal skills that the agent auto-loads — from the web settings panel and via skillmgr_* / skillmgr_extract_* tools.

DSH Skill Manager: browse, enable/disable, import from Codex/Claude Code/ZCode/WorkBuddy/QCoderWork, auto-discover skills with symlink support.

Local-first AI project orchestration workbench and CLI plugin for DeepSeek Harness: approval-gated planning, Git worktrees, task execution, Issues, and auditable evidence.

Decision split view for DSH web UI: a decision summary card in the main window plus the full plan in an independently scrollable side panel, so you can review the whole plan while writing decisions and send them back to the agent with one click.

Local image, voice, music and SFX generation plus transcription, with pinned identity: characters, animals, objects and actor voices are defined once and reused on every later call, degenerate output (a near-flat image, silent audio) is rejected instead of returned as success, and a generated line can be read back as text so a clone that swallowed its ending becomes visible. The engines unload when idle, and image generation and transcription can each be pointed at an OpenAI-shaped API instead of the local Vulkan backend.