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
Custom provider with @ai-sdk/openai-compatible silently hangs — request never sent to server #14956
Using a custom OpenAI-compatible provider (LiteLLM proxying to Ollama), OpenCode hangs indefinitely after showing build · <model>. The HTTP request never reaches the server.
Activity
github-actions commentedon Feb 24, 2026
This issue might be a duplicate of existing issues. Please check:
baseURL/apiKeyfrom config are not forwarded, causing requests to never reach the server@ai-sdk/openai-compatible), API works via curl but opencode produces no output@ai-sdk/openai-compatibleproviderPlease review those issues to see if your problem is already tracked there.
flood-runner commentedon Feb 24, 2026
Closed as duplicate of Custom OpenAI-compatible provider options not being passed to API calls #5674