anomalyco / anomalyco/opencode
RegionError "This model is not available in your country" on muse-spark-1.3-contributor from 12 different countries — gateway region gate misfiring
Nobody has claimed this yet.
- Dominant language
- TypeScript
- Stars
- 209k
- Forks
- 27.5k
- PR merge metrics
- PR metrics pending
Description
Description
Since 2026-09-08 ~11:00 UTC, all requests to muse-spark-1.3-contributor (and muse-spark-1.2-contributor) via opencode-go fail with:
{"type":"error","error":{"type":"RegionError","message":"This model is not available in your country."}}
The same model worked fine yesterday (2026-09-07) from the same setup. The error is returned before any model invocation — it is a gateway-level region check, not a model error.
This appears to be the same class of bug as #43692 / #39872 / #41518.
What rules out an actual region/IP problem
I systematically tested every hypothesis:
1. Multiple exit countries — all rejected. Switched my proxy through 12 nodes across 7 countries (all widely-supported regions), tested each:
| Node | Result |
|---|---|
| 🇺🇸 United States 01–04 | RegionError |
| 🇯🇵 Japan 01–02 | RegionError |
| 🇬🇧 United Kingdom 01–02 | RegionError |
| 🇰🇷 Korea 01 | RegionError |
| 🇩🇪 Germany 01 | RegionError |
| 🇳🇱 Netherlands 01 | RegionError |
| 🇸🇬 Singapore 01 | RegionError |
If this were a genuine geo restriction, these 7 countries would not all be rejected.
2. Both muse versions rejected, both endpoints:
muse-spark-1.3-contributorviaPOST /zen/go/v1/chat/completions→ RegionErrormuse-spark-1.3-contributorviaPOST /zen/go/v1/responses→ RegionErrormuse-spark-1.2-contributorviaPOST /zen/go/v1/chat/completions→ RegionError
3. Account/key is fine — control test passes. Same API key, same IP, same minute:
POST /zen/go/v1/chat/completions model=kimi-k3 → HTTP 200, normal completion
4. Model is listed as available. GET /zen/go/v1/models returns both muse-spark-1.2-contributor and muse-spark-1.3-contributor.
5. Minor inconsistency observed: some requests to muse intermittently return {"type":"error","message":"Internal server error"} instead of RegionError (possibly related to #40453), suggesting the gateway is currently unstable on this model family.
Repro
curl -s -X POST "https://opencode.ai/zen/go/v1/chat/completions" \
-H "Authorization: Bearer $OPENCODE_GO_API_KEY" \
-H "x-opencode-session: t1" \
-H "Content-Type: application/json" \
-d '{"model":"muse-spark-1.3-contributor","messages":[{"role":"user","content":"Reply with exactly: OK"}],"max_tokens":10}'
Environment
- Client: opencode (Bun build), model id
opencode-go/muse-spark-1.3-contributor - Subscription: OpenCode Go (active, paid)
- First failure: 2026-09-08 ~11:00 UTC (worked normally on 2026-09-07)
- In TUI the error surfaces as
AI_APICallError: This model is not available in your country.on bothbuildandtitleagents
Expected behavior
Either muse models should work from these regions as they did yesterday, or the model should be removed/region-flagged in /models. The region gate for the muse family appears to be misconfigured.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reproducing the failure with the curl request against /zen/go/v1/chat/completions and compare it with the kimi-k3 control request and GET /zen/go/v1/models. Trace the gateway region check for the muse-spark models and compare it with the behavior described in #43692, #39872, and #41518. Done means supported regions can invoke the listed models, or unavailable models are correctly removed or region-flagged.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- bun, typescript
- Domain
- api, backend
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 45/100