{"version":"2.1.242","anchor":"eval-output-options-and-judge-prompt-loosened","canonical_anchor":"eval-output-options-and-judge-prompt-loosened","heading":"Eval output options and judge prompt loosened","tier":"internal","area":"Elsewhere","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.242\/e\/eval-output-options-and-judge-prompt-loosened","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.242","markdown":"### Eval output options and judge prompt loosened\n\nEval runs can output mock call records and grade results on mock calls alone.\n\n**What**\n\nEval runs can select mock call records as an output alongside trace, last message and files, and results carry the mocks block and a flag for runs graded on mock calls alone.\n\n**Details**\n\n- The suite adoption record now tracks a separate consent decision alongside the adoption decision, both derived rather than fixed to true.\n- The judge's closing instruction, previously the hardcoded \"Respond with exactly one word: PASS or FAIL.\", is now supplied by the caller.\n\n**Evidence**\n\n`\"mock_calls\"`\n\n- Area: Elsewhere\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 2\/5"}