# 🔗 pi-mono/packages/coding-agent/CHANGELOG.md at main

- Author: @gurupanguji
- Date: 2026-04-15
- URL: https://gurupanguji.com/blog/2026/04/15/pi-monopackagescoding-agentchangelogmd-at-main/
- Categories: link
- Tags: quotes

---

> Fixed Gemma 4 thinking level mapping to route between `MINIMAL` and `HIGH`, and map Pi reasoning levels to the model's supported thinking levels ([#2903](https://github.com/badlogic/pi-mono/pull/2903) by [@aadishv](https://github.com/aadishv))

*Source:* [pi-mono/packages/coding-agent/CHANGELOG.md at main](https://github.com/badlogic/pi-mono/blob/main/packages/coding-agent/CHANGELOG.md#0671---2026-04-13)

This makes `pi` so much more useful as a local model. While I _can_ run the `gemma4:31b-it-q8_0`, the tokens per second is too slow for daily usage. However, `gemma4:26b-a4b-it-q8_0` runs fast and comes default with thinking. The fact that it can be useful as an offline model is promising. The promise of _offline_ thinking models to be run fast enough on a local computer is forever alluring. 

However, I know for sure that right now I'd rather save that money from buying a new computer and use that towards cloud token budget.