Plugins

Adaptive model routing: per-request complexity classification with automatic provider routing.

Two-level model circuit breaker with failover: trip a model or a whole provider after repeated request failures and route the next request to a configured fallback.

Zero-config Exa web search provider for the ctx.web seam: anonymous MCP fallback without an API key, plus keyed REST search.

Extends dsh-subagent-tools with a per-call cwd for subagents, shipped with the two in-process provider patches it requires.

Per-call model, provider, persona, and toolFilter overrides for subagent delegation, with @preset: references and provider/model composite ids.

Native LLM-provider vision bridge: images pasted in the chat are described by a vision model (Qwen3-VL via pi-ai/llama.cpp) and the text description is fed to text-only DeepSeek for the reply — image admission, routing and compaction all run through harness-native mechanisms, with an LRU description cache and 503 retry.

Command Code provider plugin for DeepSeek Harness (dsh) — works with every Command Code plan including the $1 Go plan; uses the Studio authentication API key over /alpha/generate, not the Provider API

fastCRW-backed web search and fetch providers for DeepSeek Harness (ctx.web)

Use ChatGPT (Codex), Claude, and Grok (X Premium) subscriptions as DeepSeek Harness LLM providers, with OAuth login from the web Settings page

SearXNG-backed web search provider for the DeepSeek Harness web capability seam (ctx.web) — self-hosted metasearch, no API key, no model turn per search

Optional provider plugin for dsh-skill-pack-security: registers the pack's skills/ (zh) or skills-en/ (en) edition on ctx.skills. Ships both editions embedded in pack/.

DeepSeek Harness plugin: AnySearch-backed web search provider (aggregates exa/tavily/firecrawl via one MCP gateway) registered into ctx.web.

Custom Claude provider support for DeepSeek Harness

Tavily search provider bundle for DeepSeek Harness (dsh): registers a WebSearchProvider into ctx.web

DSH provider plugin for Codex access through a ChatGPT subscription.

The model switch for DSH: point it at any OpenAI-compatible endpoint, with curated free/cheap DeepSeek provider presets and automatic fallback when a free tier rate-limits you.

Read-only agent-fleet credential hygiene audit: credential-file permissions, embedded credentials in git remotes (masked in output), and provider token literal counts; zero-dependency and deterministic.

Tavily-backed web search provider for the built-in web_search tool, with a settings card for the API key, result count, and recency window.

One DeepSeek Harness plugin for every pi-ai provider, including subscription OAuth

SSRF-resistant HTTP(S) fetch provider for DeepSeek Harness

Fail-closed per-turn step, tool-call, and provider-token budgets for DeepSeek Harness

OpenAI Codex OAuth provider and model adapter for dsh-oauth and DeepSeek Harness

Web access for DeepSeek Harness — multi-provider search/fetch on ctx.web, plus GitHub/PDF/YouTube extraction.

Bocha-backed WebSearchProvider and installable profile bundle for DeepSeek Harness