[eulers_secret]

Since we're talking about GitHub Copilot I'll lodge my biggest complaint about it here! The context window is stuck at 128k for all models (except maybe Codex): https://github.com/microsoft/vscode/issues/264153 and https://github.com/anomalyco/opencode/issues/5993

This absolutely sucks, especially since tool calling uses tokens really really fast sometimes. Feels like a not-so-gentle nudge to using their 'official' tooling (read: vscode); even though there was a recent announcement about how GHCP works with opencode: https://github.blog/changelog/2026-01-16-github-copilot-now-...

No mention of it being severely gimped by the context limit in that press release, of course (tbf, why would they lol).

However, if you go back to aider, 128K tokens is a lot, same with web chat... not a total killer, but I wouldn't spend my money on that particular service with there being better options!

[perryh2]

This is the first time I've read about this. Thank you. I never noticed because OpenCode just shows you the context window usage as a %.

[timr]

I mean, it's definitely not perfect, but consider that Claude is a 200k window (unless you're a beta user with access to more), and it's not the tragedy that you're making it out to be.

My experience is that the models all lose focus long before they fill their context window, so I'm not crying over the lower limit.