npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@npm-ken/pi-virtual-model

v0.3.0

Published

A virtual model router for Pi

Readme

pi-virtual-model

A phase-based virtual model router for Pi:

  • Jev selects a routing option (quick, balanced, or deep by default) for each new request. Each option specifies a model and thinking level.
  • Tool follow-ups and retries stay on the selected model. Jev also selects a model for direct requests, such as compaction summaries.
  • Jev rate-limit, gateway, and overload errors (429, 502, 503, 504, 529) are retried twice, after 250 ms and 500 ms. If all three attempts fail, the turn uses the configured fallback, including its thinking level. Authentication errors and invalid responses still surface as errors.

The extension uses TypeSafe's official Jev API: POST https://api.typesafe.ai/v1/systemone, model jev-latest, and a Choice question for routing. Obtain a key from TypeSafe.

Set [routing].api_key to a literal string or a command array that returns the TypeSafe key, for example api_key = ["fnox", "get", "THE-KEY"]. The default command reads the TYPESAFE_API_KEY environment variable. The command runs when Jev classifies a request. Each option’s thinking level controls its model’s reasoning effort.

On first load, the extension creates its global configuration at $PI_CODING_AGENT_DIR/extensions/pi-virtual-model/config.toml. When PI_CODING_AGENT_DIR is not set, it uses ~/.pi/agent/extensions/pi-virtual-model/config.toml. Edit that file to change the virtual model identity and routing options. Restart Pi after a change.

Routing options use standard TOML tables with named fields:

[virtual_model]
provider = "openai-codex"
id = "auto"
name = "Auto"

[routing]
api_key = ["printenv", "TYPESAFE_API_KEY"]
fallback = "balanced"

[routing.quick]
model = "gpt-6-luna"
thinking_level = "low"
description = "Simple questions and small, clear tasks."

[routing.balanced]
model = "gpt-6.1-sol"
thinking_level = "medium"
description = "General tasks that need moderate reasoning."

[routing.deep]
model = "gpt-6-astra"
thinking_level = "medium"
description = "Complex tasks that need careful reasoning."

The table name is the option ID. api_key and fallback are reserved settings under [routing]. Defining options replaces the default option set; fallback must refer to a defined option. Existing configurations are preserved on startup. Only the configuration format shown above is supported.

Try it

pi -e ./pi-virtual-model --model openai-codex/auto

Install it from this workspace with:

pi install ./pi-virtual-model