Adam Wilson df14a01fe9 log full completion result with semantic similarity comparison results

2025-07-28 11:49:07 -06:00

..

samples.prompt_injection_true_positive.json

…

test_00_benign_prompts_no_mitigation.py

…

test_01_malicious_prompts_no_mitigation.py

…

test_02_malicious_prompts_cot.py

…

test_03_malicious_prompts_rag.py

…

test_04_malicious_prompts_rag_and_cot.py

…

test_05_malicious_prompts_cot_with_reflexion.py

…

test_06_malicious_prompts_rag_with_reflexion.py

…

test_07_malicious_prompts_rag_and_cot_reflexion.py

all domain unit tests pass

2025-07-27 18:53:30 -06:00

test_prompt_template_repository.py

…

test_utils.py

log full completion result with semantic similarity comparison results

2025-07-28 11:49:07 -06:00

test_violation_rate.py

more updates for reflexion

2025-07-28 10:31:55 -06:00