Plugins

桌宠陪看：定时截屏，让视觉模型点评你正在看的画面，投喂给 dsh-pet 的气泡。Pet watch-along for DSH: screen sampling + a vision model + dsh-pet's bubble.

Tool-execution efficiency suite for DeepSeek Harness: read-only result cache, speculative prefetch, and concurrent readonly shell commands. Honest scope: helps when tools are slow and calls repeat; model latency dominates otherwise.

Connect multiple OpenAI-compatible providers to DeepSeek Harness: discover their models, pick the ones to expose, and generate images and videos with them from a DSH session.

Loopback-only ACP door for DeepSeek Harness: connect VS Code and other local clients to a running kernel over the local loopback address, sharing its models, tools, memory and sessions. Browse history, change permission modes and call capabilities registered by DSH plugins.

Bundles the PrismSearch MCP server and its agent skill. Web search over Bing and Baidu with no account or API key, plus Google and Brave when API keys are set and DuckDuckGo, Sogou, 360 and Yandex when enabled in config; automatic engine fallback and an aggregate mode. Also image search, WeChat Official Account article search, and fetch_page, which returns web pages and PDFs as Markdown in segments.

Registers the hosted SpecStream MCP server with the harness MCP manager and keeps the API key in the credential store. The server returns live web data as structured rows, each value with its source URL, and a run starts only after the quote's maximum is approved.

Fixes web_fetch failing with "non-public IP address" while Clash, Surge or v2rayN runs in TUN/fake-IP mode: finds your local HTTP proxy by itself, sends web_fetch through it while the proxy is on and directly when it is off, and adds an Auto/Proxy/Direct switch to the sidebar. Model calls are left alone by default.

Connects DeepSeek Harness to AIyting's image generation MCP endpoint and registers four tools: aiyting_image_catalog (models, routes and specs), aiyting_image_settings (read, quote and save parameters), aiyting_image_generate (return a quote first, and submit only with an explicit credit ceiling) and aiyting_image_task (task lookup, waiting, and a local per-account ledger for unfinished jobs). A sidebar page signs in with an AIyting access key, shows points, today's usage and daily quota, logs out, and keeps per-conversation defaults for model, route, aspect ratio, resolution and count.

TransProof translation proofreader for DeepSeek Harness: full web UI (AI translation needs your own model API key or a local Ollama endpoint) plus a local, non-networked run-local-check agent tool.

Connects DSH to timestamped video reading, shared queues/history and Scroll personal Bilibili workflows through an existing Video Reader installation. Windows x64 only: install the core and set VIDEO_READER_ROOT before starting DSH; the bundle does not install Python, FFmpeg, models or Bilibili credentials.

Localizes the prompts DeepSeek Harness sends to the model — system prompt sections, runtime context, tool descriptions and parameter docs — into Simplified Chinese. Its Cordis API dictionary is derived from zjl1989-li/dsh-harness-zh-cn (MIT), which translates the same prompt layers at runtime; do not enable both at once.

Notes-backed context compression for DeepSeek Harness: replaces LLM-summarized compaction with a model-written persistent notebook plus recoverable raw history, so the rollover boundary itself costs zero model calls.

Keep conclusions alive across context compaction: the model writes a task checkpoint and the plugin re-injects it into the system prompt's first node — the span compaction never touches, so it survives any number of compactions. Four-tier injection (0/95/175/≤12000 chars) scales with session relatedness; checkpoints live in the plugin's own folder, never in your workspace.

Keeps a turn from closing on an unfinished reply: a stream guard turns silent truncation into an in-step retry, and a completion protocol asks the model to declare how each turn ended.

Adds a relay_check tool that runs relaycheck against an LLM API relay to detect model swaps, misreported usage, truncated context and injected prompts; keys are read from environment variables.

An Auto toggle next to the model selector that schedules reasoning_effort per request: complexity is scored by a MiniMax/OpenAI-compatible model with a zero-dependency heuristic fallback (fallbacks not cached), effort ladders adapt to each model real effort list (low/high/max, low/high/highx/max/ultra, ...), heavy tool calls upgrade the tier within the same session, the lit button and reply badges show the effort actually used, and every decision plus observed token usage lands in a JSONL ledger. A standalone-button fork of imkingjh999/dsh-adaptive-effort; do not install it and the original in the same profile.

Switch OpenAI models between Codex-style Responses WebSocket transport and SSE from the composer, inheriting DSH provider settings with an optional priority-tier toggle.

Use Claude models in DeepSeek Harness through Claude subscription accounts.

Google Antigravity model provider based on LiZhenNet/dsh-antigravity, with a multi-account pool added. Do not install it in the same profile as LiZhenNet/dsh-antigravity: both register the same bundle id (dsh-antigravity) and the same npm package name.

Registers two LLM account pools as model providers: TeleAgent (China Telecom TeleAI; paste a token once) with a daily 09:00 UTC+8 full-pool check-in — currently check-in, balances and model listing only, since its chat is blocked by the client signing key — and AutoClaw (Zhipu desktop, Windows), whose tokens are decrypted from the local DPAPI-protected credential store and whose chat streams through the desktop bridge. Both pools report credit balances and model catalogs; quota-triggered failover across local desktop instances is automatic, while switching the AutoClaw account is an opt-in setting (off by default). Panels ship in settings and the left sidebar.

Bailian Token Plan quota panel using the official CLI login: 5-hour, weekly and monthly windows, add-on credits, reset countdowns and subscription status.

Shows where every session's tokens go: lifetime totals, cache hit rate, peak/off-peak cost, a calendar heatmap, a trend chart, per-model and per-workspace breakdowns, and a session tree revealing subagent sessions, with CSV/JSON export. Also ships context clear/compact actions and a prompt optimization button.

All-session token usage dashboard in the sidebar: total and peak tokens, usage streaks, a 53-week activity heatmap, 7/30-day trend, per-model usage and a session ranking. Folded locally from the profile session projection cache, so sessions written by older session formats are counted too; no network access, and the read-only summary route refuses non-loopback peers.

Peak/valley pricing and spend dashboard for DeepSeek Harness, with a sidebar pill showing today's spend and tokens plus a details page with hourly, 14-day and per-model breakdowns.