Mock all API connectors with canned ESI responses. Run:\n\n1. yentlbench run --provider api --model mock-gpt mock-claude (3 vignettes × 4 variants)\n2. yentlbench merge\n3. yentlbench analyze\n\nAssert:\n- 8 .run.json files produced (2 models × 4 variants)\n- cost_summary.json written with correct token counts\n- merged_evaluations.csv contains columns for both mock models\n- No real API endpoints called
Mock all API connectors with canned ESI responses. Run:\n\n1.
yentlbench run --provider api --model mock-gpt mock-claude(3 vignettes × 4 variants)\n2.yentlbench merge\n3.yentlbench analyze\n\nAssert:\n- 8.run.jsonfiles produced (2 models × 4 variants)\n-cost_summary.jsonwritten with correct token counts\n-merged_evaluations.csvcontains columns for both mock models\n- No real API endpoints called