Plugins

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.

OpenAI-compatible gateway adapter and dialect fixes for DeepSeek Harness

DeepSeek Harness (dsh) plugin: /refine command + settings panel for the dsh-continual-harness self-refinement engine — entry browsing, refinement history timeline, one-click rollback, auto-gate audit; engine optional at runtime.

Local tool-call failsafe for DSH: blocks a fixed list of high-risk shell patterns and credential-file reads before execution, with a per-session hash-linked JSONL audit log, and an optional external Gateway for centralized policy.

Lifecycle supervision, evidence-driven audit subagents, safe intervention, and blind acceptance gates for DeepSeek Harness

Declarative multi-agent pipeline executor for DeepSeek Harness (dsh): runs a manifest of confined role dispatches with mechanical gates and a machine-written evidence ledger. dsh 声明式多角色流水线执行器：按 manifest 派发受限子代理、机械门禁、机器写证据账本。

Comfort layer for the DSH Web UI: gentler phase/composer transitions, fused composer+stats card, auto-collapsed tool cards. Every rule is gated on <html data-dsh-comfort>; the in-UI pill toggles that attribute, so off == the stock UI exactly.

Remote access gateway for the DSH Web GUI: login auth plus an HTTP/WebSocket reverse proxy to the loopback server, no --trusted-host needed.

Taints the agent when tool results carry untrusted content, gates the privileged calls that follow, and refuses credentials passed to network-capable tools in every mode.

KiroCrew bridge for DeepSeek Harness: let your dsh agent delegate to a persistent, self-evolving KiroCrew workspace over ACP (JSON-RPC 2.0 over stdio).

DSH plugin guard: checks profile bundle lists for duplicate loader entries on every plugin load, preventing the 'duplicate loader entry id' boot crash caused by listing an aggregate bundle and its sub-plugins together — and the `dsh plugin` reconcile recu

WeChat Mini Program automated testing for DeepSeek Harness (dsh): selector-addressed actions, build-freshness gates, geometry-first assertions that work on text-only models, and screenshot image blocks on vision routes. 微信小程序自动化测试 dsh 插件：选择器寻址、构建新鲜度门、面向纯文

Deterministic aggregate media budgets and safe request projections for DeepSeek Harness (DSH)

DeepSeek Harness community Bundle for the BeforeDone evidence gate

IntelligentEyes universal agent vision gateway for DeepSeek Harness

Delegate work to external coding agents (Claude Code / Codex CLI / Grok CLI) from DeepSeek Harness: a model-facing harness_call tool, @claude/@codex/@grok mentions, live progress cards with a thinking/tool timeline, and a details side panel.

Task-queue execution endpoint for DSH: requires a separately self-deployed Hermes Agent gateway plus your own WeChat inbound script; verified on a single environment — expect to adapt it.

LLMTR AI gateway provider for the DeepSeek Harness LLM seam: 170+ chat models and Türkiye-hosted LLMs behind one OpenAI-compatible key

Spend gate for DeepSeek Harness: refuses over-budget model calls on the llm/stream waterfall, before they are billed. Auto-downgrade past a soft limit.

DeepSeek Harness bundle that registers Claw Orchestrator as an ACP subagent provider — delegate a dsh subagent to a multi-engine council across Claude Code, Codex and Cursor.

Password gate for dsh-web: opening the web port requires a username/password login; account credentials are stored salted+scrypt-hashed and AES-256-GCM encrypted in a local config file under $DSH_HOME. Host-only cordis plugin, no dsh source changes.

Password + CIDR gate for DeepSeek Harness web / DeepSeek Harness 局域网密码门禁

Generic LLM gateway model provider plugin for DeepSeek Harness: mounts newapi / LiteLLM / Higress / any OpenAI-compatible gateway as provider routes, auto-discovers the model list, enriches every model with models.dev parameters, and dispatches each model

Verification-driven self-evolution loop: failure logs become verified AGENTS.md rules; in-session plugin (evolve_learn / evolve_apply / evolve_touch / evolve_recall), tool-verify gate, rule lifecycle, local recall.