Qio

> We could prolly change it hmm hi @rekram1-node Is there anything for this issue?

> I actually merged something for this [@junmediatek](https://github.com/junmediatek) it will be in next release: > > default timeout will be 2 min, max timeout is gone (no cap) Hi @rekram1-node...

> which timeout are u wanting to set? The default? @rekram1-node Yes, I want to re-set the default bash tool for my building task that lasts up to one hour...

hi @Kreijstal I think you can refer to claude code which has BASH_DEFAULT_TIMEOUT_MS & BASH_MAX_TIMEOUT_MS environment variables, they are can be set in the setting.json file.

hi @thdxr & @rekram1-node Could you share the estimated completion time for this feature?

> yeah makes sense hi @thdxr & @rekram1-node Could you share the estimated completion time for this feature?

> no official timeline I guess we would prolly roll out experimental version first and see how it does @rekram1-node So when will the experimental version be released?

@rekram1-node & @thdxr could you help to check this issue?

hi @rekram1-node Our provider is azure , so I change to the azure ai sdk provider, however, the gpt 4.1 is ok, the gpt 5.1 failed. "gaisf-azure": { "npm": "@ai-sdk/azure",...

The root cause is the ’max_tokens‘ is deprecated in the openai API reference for reasoning models. So I think the Opencode needs to adapted this. https://platform.openai.com/docs/api-reference/chat/create#chat_create-max_tokens https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/reasoning?view=foundry-classic&tabs=REST%2Cgpt-5#api--feature-support 2 Reasoning models...