bring your own Claude / Codex / Qwen / Kimi / Copilot plan

Subscriptions#

Instead of a raw model endpoint, DGC can drive a coding CLI you already pay for and are logged into — running each turn through your own subscription.

Engines#

• Claude Code — your Anthropic Pro / Max plan (claude).
• Codex — your ChatGPT Plus / Pro plan (codex).
• Qwen Code — your Qwen OAuth plan (qwen).
• Kimi for Coding — your Moonshot plan (kimi).
• GitHub Copilot CLI — your Copilot plan (copilot).

How it works (orchestration, not a token proxy)#

This is orchestration, not credential replay. DGC never reads, stores, refreshes, or replays the vendor's tokens and never sends vendor-private headers. Each engine authenticates through the vendor's own login command, which opens the vendor's own browser / device flow and keeps the token in its own store. When you run a turn, DGC shells out to the official binary in your workspace and streams its output into DGC's UI (session, checkpoints, transcript). Selecting one is equivalent to running that CLI directly.

Select and sign in#

• dgc setup lists subscription engines first, with each one's sign-in status.
• /connect claude|codex|qwen|kimi|copilot selects an engine (a direct /connect

to a provider or URL turns delegation back off).

• Sign in once with the vendor's own command, e.g. claude auth login, codex login,

qwen (device code), kimi login, copilot login. dgc doctor reports status.

Model + reasoning effort#

• /model steers the vendor's own model (e.g. opus/sonnet/haiku for Claude).
• /think low|medium|high|xhigh sets the reasoning effort for engines that take one

(Claude, Codex, Copilot); engines without an effort flag steer it via /model.