플러그인

A dependency-free live wallpaper and theme center for the DeepSeek Harness Web UI.

DSH Web Usage Center with local SQLite history, HUD and dashboard, Hub account/quota snapshots, custom pricing and fee ledger, and CSV/JSON export, plus coding-plan OAuth and an optional loopback OpenAI/Anthropic gateway.

DSH plugin: connect to MCP servers, discover tools, and register them for direct model invocation with retry logic and statistics

DSH plugin: auto-import local AI CLI conversations (Claude Code, Codex CLI, Cursor Agent) as real DSH sessions

A floating cyber wooden fish widget — tap it to strike and accumulate merit, drag it anywhere on the page.

Remote access gateway for the DSH Web GUI: login auth plus an HTTP/WebSocket reverse proxy to the loopback server, no --trusted-host needed.

Trusted Iroh mesh networking for DSH hosts, with encrypted peer discovery, remote session delivery, and reachability status.

Taints the agent when tool results carry untrusted content, gates the privileged calls that follow, and refuses credentials passed to network-capable tools in every mode.

Runtime governor for DeepSeek Harness: zero-progress steering, generation-bound verification evidence, evidence-aware completion guarding, and task-profile tool restriction.

Capybara secretary for DSH: desktop pet notifications with ding sound, alert inbox API, session-aware alerts (turn done / approval needed / turn blocked), check scripts, and daily high-star plugin recommendations.

Scheduled bilingual financial reports for DSH: market quotes, news and macro calendar, with per-target timezones and delivery through eight dsh-im channels.

macOS system notifications for DeepSeek Harness: aborted, max-tokens, blocked, interrupted and error events, pending questions and approvals, and completion or subagent-end via terminal-notifier; clicking a banner opens a configured app and returning to the page auto-dismisses them.

Auto-continue an interrupted dsh session after a web restart by injecting a "continue" follow-up; one-shot per process, no duplicate-injection loops.

Auto Mode for DSH: a flash-model router that auto-picks the best agent preset (standard/code/minimal/cordis) for each new session and executes immediately, no confirmation.

Verification gate for DSH agents: every acceptance criterion must be backed by server-stamped real tool evidence before the completion gate lets a goal through (advisory audit, enforce gate, durable permits).

Local Windows 11 OneOCR tool for DSH: `oneocr_recognize` returns OCR text and structured line/word polygons, confidence, rotation, and handwriting style.

Local WeChat OCR tool for DSH: `wechat_ocr_recognize` returns recognized text and the engine structured result for a local image path.

Grok-compatible web search with retained source pagination, Context7 and Exa documentation lookup, bounded page extraction, site mapping, offline research planning, and read-only diagnostics.

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.

Semantic-layer analytics tool that uses curated table, column and metric metadata with Qdrant and Elasticsearch recall to generate, validate and execute MySQL analytical queries through the Xiwen service.

Local-memory lifecycle for the official Hindsight plugin on DSH desktop: one-click start/stop of the hindsight-embed daemon, auto-start on boot, stop on exit, hides the uv.exe console window, and installs the vault/models to another drive.

Group chat rooms for DSH sessions with explicit @mentions, cold-session wake-up delivery, and optional cross-host transport through dsh-weave.

Copy selections from assistant messages as Markdown, preserving links, LaTeX sources, and code-fence language info.

Configurable default model for subagent delegations via settings.yaml, with single-model and multi-model round-robin or random strategies.