v0.1.17

What's Changed

• feat: add multimodal evaluators and prompt templates for image-to-text evaluation by @sangminwoo in #187
• feat(detectors): added analyze_root_cause by @poshinchen in #179
• feat(detectors): integrated rca into evaluation workflow by @poshinchen in #210
• chore(detectors): included more fields to the RCAItem by @poshinchen in #211
• chore(detectors): updated confidencelevel and diagnose_trigger to enum by @poshinchen in #212
• feat(evaluators): added refusalEvaluator, stereotypingEvaluator, insructionFollowingEvaluator by @poshinchen in #213
• fix(experiment): preserve input order in run_evaluations_async by @poshinchen in #214
• feat(simulation): add optional tools parameter to ToolSimulator (#208) by @kaghatim in #209
• fix(evaluators): update default judge model to Claude Sonnet 4.6 by @afarntrog in #215
• chore(format): formatting by @poshinchen in #217

New Contributors

• @sangminwoo made their first contribution in #187
• @kaghatim made their first contribution in #209

Full Changelog: v0.1.16...v0.1.17