-
Notifications
You must be signed in to change notification settings - Fork 349
Vertex ai gpt-oss parsing #2847
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: canary
Are you sure you want to change the base?
Conversation
Co-authored-by: vbv <[email protected]>
|
Cursor Agent can help with this pull request. Just |
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Co-authored-by: vbv <[email protected]>
Co-authored-by: vbv <[email protected]>
Co-authored-by: vbv <[email protected]>
|
🌿 Preview your docs: https://boundary-preview-55842248-6952-4f79-9106-557cac850e29.docs.buildwithfern.com |
|
🌿 Preview your docs: https://boundary-preview-e07f8a4d-99ed-41f7-91ac-8e4440107aaf.docs.buildwithfern.com |
Pull Request Template
Thanks for taking the time to fill out this pull request!
Issue Reference
Please link to any related issues
Changes
Please describe the changes proposed in this pull request
This PR fixes a bug where the
client_response_typeoption was incorrectly sent to the Vertex AI API, causing a 400 "Invalid JSON payload" error.Specifically:
client_response_typetoUnresolvedVertexandResolvedVertexstructs.UnresolvedVertex::create_fromto consumeclient_response_typefrom the client properties, preventing it from being included in the API request body.get_response_typemethod inVertexClientto correctly determine the response parsing strategy:client_response_type.ResponseType::Anthropicifanthropic_versionis configured.ResponseType::Vertex.chat()andstream_chat()methods inVertexClientto use this newget_response_typemethod.Testing
Please describe how you tested these changes
client_response_type: "openai"to parse responses from Vertex AI models likegpt-oss-120b-maas)Screenshots
If applicable, add screenshots to help explain your changes
[Add screenshots here...]
PR Checklist
Please ensure you've completed these items
Additional Notes
Add any other context about the PR here
This change allows users to configure
client_response_type: "openai"for Vertex AI clients, enabling BAML to correctly parse responses from models that return OpenAI-compatible formats via Vertex AI's Model Garden.Slack Thread