my multi-sub setup on @omarchy: one grok bot installs agy, zcode, copilot and codex and signs in. copilot rates how hard each task is, then the bot routes it: argon/glm for hard stuff, flash/luna for easy, copilot when tokens run out.
@poteto @unclebobmartin @dhh @gregpr07
Replying to @justsisyphus
hey man, happy bday. But something wierd happening with my OmO setup since Opencode 1.1.1 released (i instruct Sysiphus, but Build executes it)
1
3
1,221
Replying to @thdxr
@thdxr hey, why do i get this error with all the Cerebras models (qwen3 and glm) I try to use in opencode via apikey? Tried with opencode auth login and /connect within Opencode, entered the right api key (even added a new one) and all good till i fire a test prompt in opencode.
1
176
Replying to @justsisyphus @opencode
ok, I was thinking in the direction of something like this optional fallback key (maybe better semantic :) )
35
Replying to @justsisyphus
@justsisyphus @opencode possible to get for core opencode.json / ohmyopencode.json agents rate limit fallbacks, so i dont have to do this (same for opencode.json)? I can try to contribute if you give me some hints for clean shot at it.
1
373







