anomalyco / anomalyco/opencode
GPT 5.6 Luna on OpenCode Go: [invalid_encrypted_content] upstream request fails with decryption error
Nobody has claimed this yet.
- Dominant language
- TypeScript
- Stars
- 209k
- Forks
- 27.5k
- PR merge metrics
- PR metrics pending
Description
Description
Bug Description
GPT 5.6 Luna model via OpenCode Go provider fails with an encrypted content
verification error. The upstream request cannot decrypt or parse the response.
Error Message
AI_APICallError: Error from provider (Console Go): Upstream request failed:
invalid_encrypted_content The encrypted content gAAA...kifQ could not be
verified. Reason: Encrypted content could not be decrypted or parsed.
Steps to Reproduce
- Subscribe to OpenCode Go
- Connect via
/connectcommand - Select
opencode-go/gpt-5.6-lunamodel - Send any prompt
- Error occurs on response
Expected Behavior
Model should respond normally like other Go models (e.g., mimo-v2.5-pro works fine).
Environment
- OS: Windows 11
- OpenCode version: 1.18.21
- Provider: OpenCode Go
- Model: gpt-5.6-luna
Logs
timestamp=2026-08-20T16:27:21.387Z level=ERROR message="stream error"
providerID=opencode-go modelID=gpt-5.6-luna
error.error="AI_APICallError: Error from provider (Console Go):
Upstream request failed: invalid_encrypted_content..."
Additional Context
Other Go models (deepseek-v4-pro, mimo-v2.5-pro) work fine on same account.
Issue appears to be specific to GPT 5.6 Luna's encrypted content handling.
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
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
No file or test is identified in the report. First reproduce the failure with opencode-go/gpt-5.6-luna on OpenCode 1.18.21, then compare its response handling with the working deepseek-v4-pro or mimo-v2.5-pro models. Done means the Luna model response is decrypted and returned without invalid_encrypted_content.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- typescript
- Domain
- ai, api
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100