Plugins

Branching surveys in the web GUI: the ask_survey tool with per-option routing, hover insights, Mermaid diagrams, quick one-click answer templates, and resumable banked progress.

Model-facing weather tool that queries current conditions and 7-day forecasts from public Open-Meteo APIs, with no API key required.

A pouch of practical micro-plugins for DSH: per-turn wall-clock time injection, safe restart, session ID header badge, Tavily search provider, configurable LLM request-header routes, and an MCP server console managing the official @deepseek-ai/dsh-mcp-client at runtime — add/edit/enable/disable/reconnect, per-tool switches, live status over SSE, mcpServers JSON import, and auto-migration of profile-YAML MCP entries.

Run the main session model on a local Claude Code subscription through the official Claude Agent SDK, taking over the llm/stream route for the claude-code provider, with token-level streaming, session resume, and DSH tools bridged in over MCP so they keep DSH sandbox and approval.

Manages the default DSH model, provider and model visibility, and optional OpenAI Responses web search.

A lightweight appearance skin for DeepSeek Harness: custom wallpaper, glass-like panel transparency, and an accent color; server-side settings shared across devices, native light/dark mode left untouched.

A QQ NT messenger skin for DeepSeek Harness: light and dark share one QQ NT language — clean restrained light mode (brand blue #12B7F5, light-blue bubbles) and a calm blue-gray dark mode (#101822) — applied as reversible token and layout layers that never touch your Light/Dark preference.

A paper-and-ink client-side theme for the DeepSeek Harness Web UI: Balanced preserves semantic status colors, and Immersive maps supported surfaces to monochrome.

DeepSeek API balance + per-call cost tracker: durable per-call cost ledger from real usage chunks with official Beijing peak/off-peak (x2) pricing, 60 s balance polling, and a sidebar footer action showing balance and today's spend.

Composer stats strip for the DSH Web UI: official CNY pricing with auto-synced peak/off-peak tiers, per-model accounting, live timers, subagent-tree merging, DeepSeek account balance, budget alerts, and streaming cost estimation.

Live remaining balance for the current API key from Sub2API, New API, or official DeepSeek, plus actual spend when the site publishes it, not a local token estimate.

Configurable VS Code style keyboard shortcuts for the DSH web GUI, with a settings-page keybinding editor, conflict detection and JSON import/export.

Third-party menu manager for the DSH Web UI: collects new menu entries added by other plugins into one place, with fold/collapse and pinned menu items.

Adds a Branch Chat tab to dsh-better-sidebar that opens independent archived sessions with a head/middle/tail context digest and the same tools as the main agent.

Web UI plugin that folds each staged response's think and tool calls into per-segment bounded, scrollable slide windows with a configurable height, keeping every intermediate response visible.

Keeps the native per-message status line always visible without hovering — date and time on every message, run duration, TTFT, and tokens per second on assistant messages.

A phone shell for the web GUI - the sidebar becomes an overlay drawer that closes when a session is tapped, the settings sheet goes full-screen single column, and the transcript is retuned for phone reading.

64-entry external CLI catalog with bounded public discovery and guarded package-manager or manual official installation, exposed through DSH tools and a standalone command.

Remote-control your dsh agent from Telegram: chat, skills, workspace browsing, and file transfer.

Backs up DSH profiles and mints a desktop "revival coin" that restores the harness after a failed boot or install: a boot guard runs a two-phase health check (HTTP 200 plus client render), marks good boots, isolates or rolls back bad ones, and keeps 3 rotating snapshots. Cross-platform.

Antigravity-style run_command for DSH: short commands return inline within a configurable wait window (default 10s) while longer ones auto-promote into ctx.jobs for later collection and completion notices — executed via ctx.shell under the session sandbox and approval pipeline.

Experience validation layer for DSH: zero-token collection of tool-failure/retry/search signals, AI refinement into verified skill books (three-layer verification), looked up at task start. Ships 10 trial skills and benchmark data (complex-task success 100% vs 60% bare).

Transparent multimodal routing for text-only models: every image in every model call is fully transcribed (verbatim OCR, data, uncertainty zones, injection-hardened) by your own multimodal understander, with focused re-look via vision_relook and automatic retry on image-related failures. No bundled endpoints, no borrowed logins.