You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Kimi K2.5 can't enable thinking (reasoning_content missing #12090
When using Kimi K2.5 via the OpenAI-compatible provider, enabling thinking does not return reasoning_content. As a result, the model behaves like non-thinking mode even when the feature should be available.
Expected behavior
Kimi K2.5 should support thinking and return interleaved reasoning content (reasoning_content) when enabled.
Steps to reproduce
Configure a Kimi K2.5 model through the OpenAI-compatible provider.
It works fine with opencode-ai@1.1.49 but is broken since 1.1.50. I just checked. Kimi K2.5 got really dumb and non-thinking. Can't make it max/high variants with ctrl+t (which is missing past 1.1.49 in TUI).
To fix this:
add "autoupdate": false in ~/.config/opencode/opencode.json
Then,
npm install -g opencode-ai@1.1.49
The kimi-for-coding provider has thinking off by default, I merged a fix to make it think by default in next release (consistent w/ other providers)
The high/max actually makes no difference in thinking u just need to explicitly turn it on for that provider. I merged a "fix" from some external contributor who cited claims from kimi team directly.
It caused this issue, but @monotykamary fixed it. you can fix temporarily using this:
"provider": {
"kimi-for-coding": {
"models": {
"k2p5": {
"options": {
"thinking": {
"type": "enabled",
"budgetTokens": 16000 // this is required for ai sdk even tho it doesnt do anything in actuality
}
}
}
}
}
}
Reacted by magicJie, Yes365, Anh Tu Tran, Huakun, Tianyu Du, Jaume Noguera, Andrew A, Omid Sayfun and 0x0000ffff
Activity
github-actions commentedon Feb 4, 2026
This issue might be a duplicate of existing issues. Please check:
Feel free to ignore if none of these address your specific case.
leosongwei commentedon Feb 4, 2026
chould be this? vllm-project/vllm#33616
docg1701 commentedon Feb 4, 2026
It works fine with opencode-ai@1.1.49 but is broken since 1.1.50. I just checked. Kimi K2.5 got really dumb and non-thinking. Can't make it max/high variants with ctrl+t (which is missing past 1.1.49 in TUI).
To fix this:
add "autoupdate": false in ~/.config/opencode/opencode.json
Then,
npm install -g opencode-ai@1.1.49
rekram1-node commentedon Feb 4, 2026
The kimi-for-coding provider has thinking off by default, I merged a fix to make it think by default in next release (consistent w/ other providers)
The high/max actually makes no difference in thinking u just need to explicitly turn it on for that provider. I merged a "fix" from some external contributor who cited claims from kimi team directly.
It caused this issue, but @monotykamary fixed it. you can fix temporarily using this: