Add request-level tests for fake models
What does this merge request do and why?
We use fake models in testing to avoid calling LLM third-party providers such as Vertex AI and Anthropic. This ensures future changes do not break this feature.
How to set up and validate locally
Numbered steps to set up and validate the change are strongly suggested.
Merge request checklist
-
Tests added for new functionality. If not, please raise an issue to follow up. -
Documentation added/updated, if needed.
Edited by Tan Le