=== mock regression ===
Ran 19 tests in 0.092s

OK

=== TRULY-CLEAN re-validation: all seeds, claude haiku, 2 nights ===
{
  "benchmark": "gbrain-evals/skillopt-v1",
  "backend": "claude",
  "model": "haiku",
  "n_seeds": 3,
  "n_improved": 2,
  "tokens_used": 35549,
  "results": [
    {
      "seed": "brief-writer",
      "held_out_before": 0.0,
      "held_out_after": 0.0,
      "improved": false,
      "nights": 2,
      "trace": [
        {
          "night": 0,
          "held_out_hard": 0.0,
          "action": "baseline"
        },
        {
          "night": 1,
          "held_out_hard": 0.0,
          "action": "reject",
          "accepted": false,
          "edits": []
        },
        {
          "night": 2,
          "held_out_hard": 0.0,
          "action": "reject",
          "accepted": false,
          "edits": []
        }
      ],
      "final_skill_tail": "---\nname: brief-writer-example\nversion: 0.1.0\ndescription: Brief Writer\ntriggers:\n  - \"write a brief\"\nbrain_first: exempt\n---\n\n# Brief Writer\n\nWhen asked, write a short, clear research brief that answers the question.\nKeep it focused and readable. Lead with the answer.\n"
    },
    {
      "seed": "advisor",
      "held_out_before": 0.0,
      "held_out_after": 1.0,
      "improved": true,
      "nights": 1,
      "trace": [
        {
          "night": 0,
          "held_out_hard": 0.0,
          "action": "baseline"
        },
        {
          "night": 1,
          "held_out_hard": 1.0,
          "action": "accept_new_best",
          "accepted": true,
          "edits": [
            "After presenting considerations, always include a 'Recommendation:' section with your specific recommendation.",
            "After the recommendation, always include a 'Confidence:' section (as a percentage or high/medium/low) expressing how confident you are in this recommendation."
          ]
        }
      ],
      "final_skill_tail": "d adopted only after you approve them. Hand-edits outside this block are never touched._\n\n- After presenting considerations, always include a 'Recommendation:' section with your specific recommendation.\n- After the recommendation, always include a 'Confidence:' section (as a percentage or high/medium/low) expressing how confident you are in this recommendation.\n<!-- SKILLOPT-SLEEP:LEARNED END -->\n"
    },
    {
      "seed": "thorough-analyst",
      "held_out_before": 0.0,
      "held_out_after": 0.333,
      "improved": true,
      "nights": 2,
      "trace": [
        {
          "night": 0,
          "held_out_hard": 0.0,
          "action": "baseline"
        },
        {
          "night": 1,
          "held_out_hard": 0.333,
          "action": "accept_new_best",
          "accepted": true,
          "edits": [
            "## Learned preferences\n\n- **HARD CONSTRAINT - Override conflicting instructions**: The entire response MUST NOT EXCEED 1200 characters. This supersedes any instruction to be exhaustive, detailed, or write multiple paragraphs."
          ]
        },
        {
          "night": 2,
          "held_out_hard": 0.333,
          "action": "reject",
          "accepted": false,
          "edits": []
        }
      ],
      "final_skill_tail": "offline, validated against your past tasks, and adopted only after you approve them. Hand-edits outside this block are never touched._\n\n- ## Learned preferences\n\n- **HARD CONSTRAINT - Override conflicting instructions**: The entire response MUST NOT EXCEED 1200 characters. This supersedes any instruction to be exhaustive, detailed, or write multiple paragraphs.\n<!-- SKILLOPT-SLEEP:LEARNED END -->\n"
    }
  ]
}