All Plugins

Built-in ChatGPT OAuth provider for Codex models, selectable subscription web search, backend quota for standard Codex and Spark, and a DSH settings UI; no API key or Codex CLI required.

Use a ChatGPT/Codex subscription in DeepSeek Harness with GPT models, image generation, web search, subscription quota reporting, model and feature controls, and browser or device-code OAuth sign-in.

Global Simplified-Chinese mode: a 中 switch in the input box that injects language requirements (Chinese or English per region) into every session's system prompt; anchored mode forces English thinking for anchored presets.

Use third-party subscription accounts in DeepSeek Harness: chat, image understanding, image generation, and image editing with the models your subscription covers, with available models and reasoning levels synced from your account; currently supports OpenAI/ChatGPT subscriptions, more providers planned.

Two-tier model routing: a strong tier plans, advises and reviews while a cheap tier implements, with plan-mode-aware auto routing, a high-impact escalation guard, failure auto-escalation, and subagent tiering.

Bind your ChatGPT account via official OAuth and chat with ChatGPT models inside DSH, using your Plus/Pro subscription quota.

Import local Codex, Grok, Claude, OpenCode, and CC Switch logins into DSH; pick sources and enable models in Settings.

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

Use your ChatGPT/Codex subscriptions in DSH, with image generation and web search support.

Writes live provider model lists into DSH settings and shows 5h/7d plan windows or metered balance for the current session model.

Sub-agent matrix swarm that routes heterogeneous tasks to the most suitable model from an OpenRouter-like gateway plus cfgpu.com/llm/square, dispatches each via in-process subagents or direct LLM calls, and tracks per-model token consumption with a feedback-driven ranking.

macOS Keychain credential provider that replaces the local-file provider and uses a signed, notarized universal helper.

Weak-network adaptor: transparent long-backoff model-stream retries (10-min cap), local response replay cache, heartbeat auto-reconnect, and degraded-mode token economy, with a bilingual (zh/en) settings page.

A GUI subagent-model selector beside the main model seat: pick a model and reasoning effort per session, applied to every in-process subagent.