Plugins

Voice announcements when a conversation ends (session title, round, outcome) plus live sentence-by-sentence reading of replies, via built-in edge-tts with zero third-party dependencies.

Dual-MediaPlayer daemon ($think loop + $fx one-shots) with volume ducking, mood-aware sounds (smooth/struggle/deep_think triggered by consecutive success/failure streaks and prolonged agent runtime), 15 built-in PCM WAV synthesised from sine/square waveforms, per-tool sound mapping with 51 categorised tools, custom WAV/MP3 drop-in with auto-conversion, and a full settings UI with dark-mode fix.

Turn every idea into an image or video with Kling AI. In DeepSeek Harness, use natural language for text-to-image, image-to-image, text-to-video, image-to-video, reference-image creation, task tracking, and result previews.

Auto-switch the DeepSeek route to the vision model on demand: flash main session switches (A), pro keeps deep reasoning and delegates image reading to a vision subagent (B), subagents always switch, with fatal-failure fallback. No manual model switching.

WebMCP bridge: your agent discovers & calls site tools exposed over the W3C WebMCP protocol via a built-in headless Chromium.

Force the agent's chain-of-thought, planning, tool-invocation reasoning, and internal deliberation to stay in Chinese — the language constraint is injected at the top of the system prompt before every reasoning step, so it cannot be diluted by tool-returned content. A settings panel lets you edit the constraint text on the fly.

Knowledge base (Vault memory + knowledge graph) for dsh: kb__* tools for deterministic memory search/write, knowledge-graph nodes/edges/subgraph/traversal, document-to-graph ingestion and unified cross-store query (KAL) - no web-search tools.

Redirects DSH downloads, artifacts, caches and temp files to user-specified drives (auto-picks the largest non-C drive), injects a path-discipline prompt into every session, and ships a disk_guard tool for status and cleanup — keeps the C: drive from filling up.

Linux X11 computer use for DeepSeek Harness: 9 tools (screenshot, move/click/drag/scroll mouse, type, key combos) driven by a zero-dependency Python XTest helper — native-pixel coordinates, per-action verification, optional auto-observation screenshot.

Analyze the current branch diff and generate a Conventional Commits PR title, motivation/scheme/testing/risk description and a self-review checklist, write PR_DESCRIPTION.md, optionally open the PR via gh.

Expose a local MCP server to remote agents through an outbound-only tunnel stack (mcp-proxy + cloudflared Quick Tunnel), then register the public URL into dsh-mcp-client streamable-http config.

Scan project lockfiles (npm/pnpm/yarn/pip/go/cargo/maven/gradle/...) against the free OSV API and report confirmed dependency vulnerabilities with fix versions and remediation commands.

Per-workspace memo/todo panel that auto-captures queued and running user instructions, marks preempted tasks as interrupted, and restores them to their previous state with one click.

Permanent memory plugin for DSH with vector search, LLM reflection, and knowledge pages.

Tiered compaction hub: replaces the single 80% compaction cliff with a configurable ladder (default 30/50/70/90) whose tiers escalate from gentle to maximum consolidation laws, folds a deterministic keyword index into every checkpoint so facts accumulate across cycles, and summarizes through a model chain — primary plus up to 3 fallbacks, each with its own reasoning effort. Adds a Compaction module sub-tab and a Settings card; toggling off always restores stock compaction.

Adds confirmed DSH restart actions and durable automatic continuation for eligible top-level sessions through an existing compatible dsh-restart Host provider.

OAuth sign-in for 9 subscription LLM providers (Claude, Codex, Grok, Antigravity, OpenRouter, Agnes AI, Qwen, Spark, ERNIE) with zero-config login and usage dashboards.

Replaces the official Models settings page with provider lifecycle management, per-model reasoning effort tiers, retry overrides, drag reorder and upstream model sync.

Control panel for local LLM inference servers in the DSH web view: service registry with health checks and stop controls, named parameter profiles for llama.cpp, SGLang and vLLM with pre-save KV/VRAM validation, GPU detection, and tok/s benchmarks.

Manage multiple API keys per provider in Settings → API 密钥: keep a pool of keys with notes, switch the active key with one click, and the switch really takes effect on the next model call.

Adds a /dshpp slash command that reports session and token usage, cache-hit rate, and estimated cost from harness session logs; the repo also ships a CLI and local web console for lifecycle, provider, session, and plugin-security management.

A draggable Volcengine Coding Plan usage card for DeepSeek Harness Web using a local console session.

DeepSeek balance and per-session cost in the DSH web composer dock, with official peak/off-peak pricing (peak hours Mon-Fri BJT 9-12 / 14-18, weekends off-peak) and built-in deepseek-v4-flash-vision-exp vision model rates billed at flash price (images billed as tokens, max 384 tokens each).

Peak and off-peak pricing-period indicator for the DeepSeek API in the DSH chat UI, with a countdown to the next period and an API balance readout on hover.