When use gpt-oss-120B by vLLM locally, opencode doesn't call the tools

Open inv1s10n opened this issue 1 week ago • 13 comments

Description

When I try use local model (such as gpt-oss-120b and qwen3-32b), there is only content of thinking in response, no tools calling(even if model thinks it should call tools from thinking content) and no other response. But sometimes it be normally(very rare). This is very strange.