Plugins

Nous Portal free-tier provider for dsh: Portal OAuth (device-code) agent-key lifecycle behind an OpenAI-compatible harness route

DSH web plugin that ranks OpenRouter upstream providers by quality, speed, cache-heavy price, context, and uptime, then safely switches the active route.

Per-model reasoning effort declarations for GPT, Gemini and OpenAI-compatible providers in DeepSeek Harness

将 DSH 聊天框模型选择改为先选择供应商、再选择模型。

DeepSeek balance & token-cost plugin for DeepSeek Harness (dual-face): query official balances of every DeepSeek provider (multi API key), compute costs (last question / session / today-project / today-all) from token usage with a user-editable price tabl

AI Agent runtime authorization & evidence verification — tool-call GuardrailProvider, CCS 7-dimension verification standard, MCP/DSH security scanner, SSRF/command-injection/credential-exfil blocking with Ed25519 signed receipts.

Route fresh DeepSeek Harness subagents to registered provider/model pairs declared in role Markdown files

Register AllRouter as a DSH provider: one base URL and one key for Kimi K3, Claude, GPT, Grok, GLM, DeepSeek, MiniMax-H3. Switch models without managing separate providers; every call reports real cost.

Provider-neutral search and extraction tools for DeepSeek Harness

LLM compatibility auto-healer: detects 400 errors from incorrectly declared model capabilities (thinking/reasoning) on transit/gateway providers, then idempotently patches `llm-pi-ai` config and suppresses thinking on the next request — no restart needed. Full settings UI for every pi-ai compat field.

LiteLLM /v1/search-backed web search provider for the DeepSeek Harness web capability seam (ctx.web). One search is one HTTP request — no model turn.

Multi-key Tavily search provider for DeepSeek Harness (ctx.web) with a live settings card in the web plugin configuration page

Calendar todo plugin for the dsh web GUI: a sidebar entry plus a week/month calendar where you drag-select time ranges to create tasks, with Eisenhower urgency/importance quadrants, subtasks, pinned execution session + LLM provider, and host-authoritative

Use ChatGPT (Codex) subscription as a DeepSeek Harness LLM provider via OAuth — standalone plugin, no upstream patching, proxy-aware.

DeepSeek Harness adapter for Qwen Token Plan CN with Responses tools, GLM Chat routing, and a versioned official catalog

CommandCode Go 套餐供应商：/alpha/generate CLI 网关接入 DSH 模型列表 + OAuth 登录（设置页 CommandCode Go 登录选项）

Provider baseURL auto-detection: when a provider's baseURL is a bare domain (e.g. `https://mzeapi.top`) and only `/v1` serves the OpenAI-compatible API, the plugin auto-fixes it — probes all providers with zero-cost path detection (no API key needed).

Use OpenCode models inside DeepSeek Harness without a separate provider API key.

Brave Search API-backed web search provider for the DeepSeek Harness web capability seam (ctx.web)

Rate-limit plugin for DeepSeek Harness: FIFO queue per provider/model bucket with minIntervalMs and maxConcurrent

OpenAI-compatible LLM adapter plugin for DeepSeek Harness with configurable default sampling parameters (temperature / topP / topK / penalties / seed) over a providers dict.

Host-anchored provider, authentication, catalog, policy, and model-selection extension for DeepSeek Harness.

New API OAuth provider, account configuration, model discovery, and model adapter for DeepSeek Harness

Provider-neutral OAuth account and credential lifecycle foundation for DeepSeek Harness