Description
Describe the bug
After logging in with opencode-go subscription, every model call uniformly throws error:
Request blocked by upstream provider.
No single model under opencode-go subscription can complete any chat/completion request.
Steps to reproduce
- Install latest opencode release
- Run
opencode TUI, execute /login
- Select
opencode-go subscription auth flow, complete login normally
- Switch any model under opencode-go provider
- Send any prompt to trigger model inference
- Error pops up immediately without any response content
Expected behavior
All subscribed opencode-go models should normally complete LLM inference requests without upstream block error.
Actual behavior
Every model request returns identical error message:
Request blocked by upstream provider.
No logs with detailed upstream status code, no retry logic takes effect.
Environment
- OS:
- OpenCode version:
opencode --version
- Bun version:
bun --version
- Network: Direct connection / proxy
Additional context
- All models under opencode-go subscription are affected; no single model works.
- No rate limit prompt, no API key expired reminder, only upstream block message.
- Cleared local auth cache
~/.local/share/opencode and re-login multiple times, issue persists.
- Other third-party API key providers (openai compatible) work fine, only opencode-go subscription auth is blocked upstream.
- No custom modified config, default opencode.json with zero custom provider overrides.
Verification I've completed
Plugins
No response
OpenCode version
v1.18.4
Steps to reproduce
No response
Screenshot and/or share link
No response
Operating System
No response
Terminal
No response
Description
Describe the bug
After logging in with opencode-go subscription, every model call uniformly throws error:
Request blocked by upstream provider.No single model under opencode-go subscription can complete any chat/completion request.
Steps to reproduce
opencodeTUI, execute/loginopencode-gosubscription auth flow, complete login normallyExpected behavior
All subscribed opencode-go models should normally complete LLM inference requests without upstream block error.
Actual behavior
Every model request returns identical error message:
Request blocked by upstream provider.No logs with detailed upstream status code, no retry logic takes effect.
Environment
opencode --versionbun --versionAdditional context
~/.local/share/opencodeand re-login multiple times, issue persists.Verification I've completed
Request blocked by upstream providerbug, no duplicate ticket foundPlugins
No response
OpenCode version
v1.18.4
Steps to reproduce
No response
Screenshot and/or share link
No response
Operating System
No response
Terminal
No response