anomalyco / anomalyco/opencode

WSL: opencode-go Forbidden intermittently — works fine on Windows with same IP/version

Open
#44,390 2 comments 0 reactions 1 assignee View on GitHub

@MrMushrooooom is already working on this.

Since Aug 23, 2026.

Dominant language
TypeScript
Stars
209k
Forks
27.5k
PR merge metrics
PR metrics pending

Description

Description

Environment

  • OpenCode version: 1.18.18 (both WSL and Windows)
  • OS: WSL2 Ubuntu 22.04 (kernel 6.18.33.2) + Windows 10
  • Public IP: same for both (101.87.170.107)
  • Provider: opencode-go (Go plan)

Problem

WSL Linux build gets AI_APICallError: Forbidden on opencode-go API calls.
Windows build with the same account/IP/version works perfectly.

The error is intermittent — sometimes it works, sometimes it doesn't.
Total Forbidden errors in today's log: 140

Affected models (from log)

  • deepseek-v4-flash (36 errors)
  • deepseek-v4-pro (18 errors)
  • deepseek-v4-flash-free (16 errors)
  • ox-alpha-free (3 errors)
  • x-preview-f-free (2 errors)
  • big-pickle (2 errors)

Both opencode-go (57 errors) and opencode (20 errors) providers are affected.

Additional evidence

  • https://models.opencode.ai/api.json also returned 403 at times from WSL
  • All API endpoints (api.opencode.ai, gateway.opencode.ai) are reachable from WSL
  • Same auth.json key is used on both sides

Log excerpt

timestamp=2026-08-23T11:36:13.268Z level=ERROR message="stream error" providerID=opencode-go modelID=deepseek-v4-flash error.error="AI_APICallError: Forbidden" timestamp=2026-08-23T11:40:03.124Z level=ERROR message="Failed to fetch models.dev" cause="403 GET https://models.opencode.ai/api.json"

Expected behavior

WSL should work the same as Windows since they share the same network and account.

Plugins

No response

OpenCode version

No response

Steps to reproduce

No response

Screenshot and/or share link

No response

Operating System

No response

Terminal

No response

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.