News for hackers. Stuff that matters.
Re:ZCode: Claude Code from the Makers of GLM by daytonix on Wednesday July 01, 2026 @03:59PM (#48752334)
have used both pi and opencode for the last 6 months, haven't opened a proprietary harness (cc, codex, cursor) in that same amount of time. right now i'm on pi and i can switch seamlessly between any model across any provider i want, even mid session. can even point them at locally running models.

i think people don't realize how much better life is over on this side, cc and codex rely entirely on vendor lock in imo.

Re:ZCode: Claude Code from the Makers of GLM by l00sed on Wednesday July 01, 2026 @04:02PM (#48752369)
Haha I pretty much commented the same thing one minute apart.
Re:ZCode: Claude Code from the Makers of GLM by esafak on Wednesday July 01, 2026 @04:12PM (#48752488)
why did you switch from oc to pi?
Re:ZCode: Claude Code from the Makers of GLM by daytonix on Wednesday July 01, 2026 @04:25PM (#48752649)
i like the more minimal design of the tui, feels more integrated with my existing terminal workflows. oc always looked a little out of place. i really like pi's extension ecosystem as well.
Re:ZCode: Claude Code from the Makers of GLM by alexfortin on Thursday July 02, 2026 @02:09AM (#48757190)
Same here. Moving from OC to Pi also taught me one more time that less is more and I don't need most of the features I thought I needed.
Re:ZCode: Claude Code from the Makers of GLM by mr_mitm on Wednesday July 01, 2026 @04:25PM (#48752645)
You can use Claude Code with a self hosted model no problem. I don't believe you can switch during a session though.
Re:ZCode: Claude Code from the Makers of GLM by fcarraldo on Wednesday July 01, 2026 @05:00PM (#48753055)
Does a mid-session provider switch result in loading the entire context into the new model, inflating session cost?

I don't think I understand the token/cost implications of this feature

Re:ZCode: Claude Code from the Makers of GLM by gunalx on Wednesday July 01, 2026 @06:12PM (#48753818)
Its nice if you used local, but needed å beefier modell, or more context Window. It will eat input tokens, but you do that all the time unless you have input caching.
Re:ZCode: Claude Code from the Makers of GLM by resonious on Thursday July 02, 2026 @12:29AM (#48756582)
Yes you pay a big burst right after switching. After that, everything is cached and it's smooth sailing.
Re:ZCode: Claude Code from the Makers of GLM by FergusArgyll on Wednesday July 01, 2026 @06:09PM (#48753791)
codex is open source https://github.com/openai/codex/ it's definitely geared towards openai but it is completely open source
Re:ZCode: Claude Code from the Makers of GLM by jcmfernandes on Wednesday July 01, 2026 @08:38PM (#48754950)
Are you using openrouter or something else?
Re:ZCode: Claude Code from the Makers of GLM by try-working on Thursday July 02, 2026 @01:03AM (#48756754)
Try the role-model Pi extension I built, to let Pi determine when to switch to a different model in your pool.

https://github.com/try-works/role-model