Request Failed (400) with Enterprise BYOK Models
Open
info-needed
model-byok
- Dominant language
- TypeScript
- Stars
- 193k
- Forks
- 42.4k
- PR merge metrics
- PR metrics pending
Description
Does this issue occur when all extensions are disabled?: Yes/No
"Request Failed: 400 {"error":{"message":"Unsupported parameter: 'max_tokens' is not supported with this model. Use 'max_completion_tokens' instead.","code":"invalid_request_body"}}" when use GPT-5.5 and GPT-5.6 sol only on VS Code. It's working on JetBrains IDEs and on GHCP CLI.
- VS Code Version: 1.137.0
- OS Version: Windows_NT x64 10.0.26200
Steps to Reproduce:
1. Open GHCP Chat in VS Code
2. Select the Foundry Model via Enterprise BYOK
3. Ask anything in the chat (Agent Mode)
Contributor guide
Assessment
This issue has not been assessed yet.