@openference/pi-provider

Official Openference provider for Pi — device-flow OAuth login, live model discovery, and plan-aware pacing

Packages

Package details

extension

Install @openference/pi-provider from npm and Pi will load the resources declared by the package manifest.

npm repohome report
$ pi install npm:@openference/pi-provider
Package
@openference/pi-provider
Version
0.1.1
Published
Jul 30, 2026
Downloads
276/mo · 13/wk
Author
anhlead
License
MIT
Types
extension
Size
57.4 KB
Dependencies
0 dependencies · 2 peers
Pi manifest JSON
{
  "extensions": [
    "./src/index.ts"
  ]
}

Security note

Pi packages can execute code and influence agent behavior. Review the source before installing third-party packages.

README

@openference/pi-provider

Official Openference provider for Pi.

Signs in with the same Openference OAuth device flow used by first-party apps: Pi prints a link you click or copy into a browser, you approve, and models load automatically with correct context windows, pricing, and plan-aware request pacing.

Install

pi install npm:@openference/pi-provider

Restart Pi, then:

/login openference
/model openference/GLM-5.2

Choose Browser link when prompted. Open the printed URL, sign in to Openference if needed, and approve. Pi stores tokens in ~/.pi/agent/auth.json.

You can also paste an API key (secondary option) or set OPENFERENCE_API_KEY.

What this package configures

  • Live model list from GET /v1/models (respects your key’s model restrictions; run /reload after changes)
  • Safe context windows and max output tokens so Pi compacts at the right time
  • Thinking / reasoning levels from each model’s supported efforts
  • Soft pacing from your plan’s RPM limit, and correct handling of Retry-After on rate limits
  • Automatic recovery when a prompt exceeds the model context

If you keep hitting plan limits, upgrade or add credits — the package already respects your allowance.

References