Plugins

面向 DeepSeek Harness Standard 的 DeepSeek V4 首轮 RL 锚定插件，promotion 后恢复完整能力与 Skill。

DSH Web GUI 模型能力配置：在「设置 → 模型」的模型目录编辑器内，为每个已配置的模型直接设置是否支持图像与思考等级（reasoning efforts），写入 llm-pi-ai 设置命名空间。

Token usage dashboard, provider balances, and subscription quotas for the dsh web GUI

DeepSeek Harness plugin: live account balance/quota panel for every configured LLM provider (sidebar widget, configurable refresh interval)

Cline free models provider for dsh: scan the Cline model catalog dynamically and serve the :free models through the harness LLM seam

Put a dsh (DeepSeek Harness) workspace on ANY machine. Two modes in one plugin: (1) fleet — enroll an off-site machine behind NAT into your dph via a one-time token + reverse tunnel to your own relay VPS, so it appears as a dsh-ssh host; (2) execution wor

Global experience archive for DeepSeek Harness on Windows: probes local tools (with versions and PATH-first hits), convenient paths, network latency and disk speed; folds per-session stats from session/event; LLM-extracts durable facts; env_profile tool with remember; byte-stable summary injected every turn to speed up sessions and cut token use.

DeepSeek Harness out-of-tree plugin: give a text-only coding model eyes by routing images to a Qwen-VL (DashScope) route through ctx.llm and returning text.

DIT.ai provider bundle for DeepSeek Harness: installs 29 OpenAI Chat Completions models and 10 Anthropic Messages models from one DIT_API_KEY, with protocol-specific thinking configuration.

The DeepSeek time-of-use meter for dsh: what this session cost, which tariff is running, when it flips, and the account balance behind it — one line under the composer.

Fail-closed LLM-assisted approval reviewer for DeepSeek Harness

Autonomous permission classifier for the auto preset: tool-scoped allow/deny rules, an LLM semantic judge, and git checkpointing for unattended sessions.

Exposes bounded Prometheus metrics for DSH sessions, agents, LLM calls, tools, approvals, subagents, and jobs, with a Grafana dashboard and a loopback-only endpoint by default.

Contract regression harness for plugin authors: a scripted LLM adapter drives the real pipeline in isolated child processes with session-event assertions (load/contract/behavior/fault layers); zero API key, CI-ready.

Vision-augmented DeepSeek adapter: a vision-capable model describes image input, then a text-only DeepSeek model reasons over the description.

Plug-in vision for text-only models on DSH, with native interaction for image understanding and generation, GUI automation, through layered evidence memory and cache.

Synesthesia Encoder for DSH: a vision model translates images into compact structured spatial text (canvas/elements/percentage coordinates), giving text-only LLMs pixel-level image understanding via the `mm_vision` tool.

xAI Grok subscription chat: SuperGrok or X Premium+ OAuth, a displayed model subset, Responses through the Grok CLI proxy, and always-on server-side web_search and x_search.

Unofficial Cursor subscription chat: Host-owned CLI session login, a displayed model catalog, and subscription usage rails. Cursor staff treat this class of private-client usage as against ToS.

Automatic provider failover on rate limits or quota exhaustion: switch between providers with configurable per-provider models, a cooldown, and a permanent last-entry fallback.

Token usage statistics for DeepSeek Harness. Per-channel usage with balances and plan quotas for mainstream providers, CNY cost estimates, and daily charts — a settings-sidebar section.

Persistent provider-reported token usage totals with per-session, per-model, and daily activity statistics.

Live per-task token cost widget: peak/valley pricing windows, projected post-hike costs, sortable per-task cost table, multi-currency (COP/USD/CNY + ~40 more) with FX rates, and one-click streamed LLM explain of expensive tasks.

Vendor-based usage dashboard: per-provider token/cache/output KPI, a 53-week heatmap, trend chart with hourly "today" view, model drilldown, cost estimation, CSV export, and health cards (TTFT, generation speed, peak context, error rate).