Problem
ucode registers Databricks GPT models as custom openai-responses models in Pi. Without model-specific thinkingLevelMap metadata, Pi exposes its generic thinking levels for every GPT model. Selecting an unsupported level can cause the Responses API or Databricks AI Gateway to reject the request.
For example, GPT-6 Astra supports low, medium, high, xhigh, and max, but does not support none. GPT-5.4/5.5/5.6 and Pro variants have different supported subsets.
Proposed fix
Declare model-specific Pi reasoning metadata and map Pi's off choice to the Responses API's none value only for models that support it. Hide unsupported minimal, low, or off choices where necessary.
A focused implementation and regression tests are included in the accompanying pull request.
Problem
ucode registers Databricks GPT models as custom
openai-responsesmodels in Pi. Without model-specificthinkingLevelMapmetadata, Pi exposes its generic thinking levels for every GPT model. Selecting an unsupported level can cause the Responses API or Databricks AI Gateway to reject the request.For example, GPT-6 Astra supports
low,medium,high,xhigh, andmax, but does not supportnone. GPT-5.4/5.5/5.6 and Pro variants have different supported subsets.Proposed fix
Declare model-specific Pi reasoning metadata and map Pi's
offchoice to the Responses API'snonevalue only for models that support it. Hide unsupportedminimal,low, oroffchoices where necessary.A focused implementation and regression tests are included in the accompanying pull request.