Repository navigation
[FEATURE]: Discover vLLM models out of the box on dev (port of #43022) #47344
Description
Feature hasn't been suggested before.
- I have verified this feature I'm about to request hasn't been suggested before.
Describe the enhancement you want to request
Pointing OpenCode at a vLLM server today means hand-writing a custom @ai-sdk/openai-compatible provider: model IDs, context limits, and for thinking models like Kimi K2 also "interleaved": "reasoning_content", otherwise the second turn fails with Assistant message is missing a thinking field. Provide one of: think, reasoning, reasoning_content, ....
The v2 branch already discovers vLLM models automatically (#43022, #43589), but none of that is in the current dev releases (1.18.x).
Proposal: a built-in vllm provider plugin on dev that reads /v1/models, uses max_model_len as the context limit, defaults reasoning_content interleaving, and takes the endpoint from VLLM_BASE_URL or provider.vllm.options.baseURL (optional API key). Zero config for a local server on 127.0.0.1:8000, one env var for a remote GPU box.
Activity
old-square-eyes commentedon Sep 11, 2026
Confronting this now. Seems like a no brainer to discover current available models? I thought local model support was a first class feature?
old-square-eyes commentedon Sep 11, 2026
Also someone actually did a PR and it was rejected?
neriousy commentedon Oct 19, 2026
v2 discovers vLLM models out of the box: with vLLM at
http://127.0.0.1:8000it checks/health, lists/v1/modelsand usesmax_model_lenas the context limit, so models appear asvllm/<model>with no config. For another endpoint or an authenticated server, setproviders.vllm.settings.baseURLandapiKey. This is available since v2.0.0. To get v2:npm i -g @opencode/cli@latestorcurl -fsSL https://opencode.ai/v2/install | bash(desktop: update the app). If you still see this on v2, please open a new issue with the details.