Re:Kimi K2.7 Code is generally available in GitHub Copilot
by c7b on Thursday July 02, 2026 @10:41AM
(#48762363)
Cool! Anything you want to share? I haven't looked much into my system prompt yet, do you have any tips?
[ Parent
| on HN ]
Re:Kimi K2.7 Code is generally available in GitHub Copilot
by cyanydeez on Thursday July 02, 2026 @04:56PM
(#48767258)
so opencode has multiple agents for the primary, and that's all I'm doing _but_, I pair it with llamacpp for thinking mode:
--reasoning-budget N token budget for thinking: -1 for unrestricted, 0 for immediate end,
N>0 for token budget (default: -1) (env: LLAMA_ARG_THINK_BUDGET)
--reasoning-budget-message MESSAGE message injected before the end-of-thinking tag when reasoning budget
Currently, opencode doesn't do this, but the budget-message could be implemented by a harness to put in custom message. So I tailored an agent with a message that has it either compress the context via dynamic compression plugin or request that it uses a subagent to avoid bloating the context.
It's mildly successful, but you can tell as context size grows it becomes more and more narrow sited or wayward.