@opeoginni/opencode-copilot-autoAdd GitHub Copilot Auto model routing to OpenCode
3
203
42 in 7 days
39.1
Multi-signal model
4 days ago
2026-08-15
Install and configure
opencode.jsonWrites to this project's opencode.json — applies to this repository only.
opencode.json
{
"$schema": "https://opencode.ai/config.json",
"plugin": ["@opeoginni/opencode-copilot-auto@0.1.8"]
}Writes to ~/.config/opencode/opencode.json — applies to every project.
~/.config/opencode/opencode.json
{
"$schema": "https://opencode.ai/config.json",
"plugin": ["@opeoginni/opencode-copilot-auto@0.1.8"]
}If you want to modify the plugin locally, install it into the project and reference the local path.
shell
pnpm add -D @opeoginni/opencode-copilot-autoopencode loads npm dependencies through its embedded runtime on startup and caches them locally — no manual global install needed.
Adds GitHub Copilot's Auto model to OpenCode. Copilot selects the appropriate available model for every request.
Install
Add the plugin to opencode.json:
{
"$schema": "https://opencode.ai/config.json",
"plugin": ["@opeoginni/opencode-copilot-auto"]
}
Restart OpenCode, authenticate GitHub Copilot if necessary with opencode auth login, then select github-copilot/auto.
The plugin uses the existing OpenCode GitHub Copilot authentication and sends the prompt to Copilot's routing endpoint solely to select a model.
Commands
/copilot-refresh: Clears the routing cache so the next prompt selects a fresh model./copilot-autorefresh: Toggles fresh model selection for every prompt. Run it again to resume using the cached routing session./copilot-notify: Toggles notifications between a toast and the projection bus.
Development
bun install
bun run check
bun run test
bun run build