- Issue created by @marcus_johansson
- π¨π¦Canada bisonbleu
Attaching example terminal output for
ddev drush agents:test-agents --group_id=1 --uid=1
- π¨π¦Canada bisonbleu
Attaching example terminal output when overriding the LLM evaluation model.
ddev drush agetes --group_id=1 --uid=1 --eval_provider=openai --eval_model=o3
- π¨π¦Canada bisonbleu
Added a 3rd test to the group that asserts basic_page content type is not promoted. This will of course fail.
- π¨π¦Canada bisonbleu
Bonus, added approximate execution timeβ¦
- π¨π¦Canada bisonbleu
And what it looks like in detailed modeβ¦
- π¨π¦Canada bisonbleu
How to test:
- Install & Enable ai_agents_test;
- Download test_basic_pages_test_group.yaml.txt and remove the trailing
.txt
; - Go to admin/content/ai-agents-test/group and import the .yaml file;
- Run e.g.
drush agetes --group_id=1 --uid=1 --eval_provider=openai --eval_model=o3 --detailed