{
  "schema": "results.v1",
  "run": "2026-10-21-phase-announced",
  "dataDate": "2026-10-21",
  "runsFrom": "2026-10-21T14:22:58.375484Z",
  "runsTo": "2026-10-23T05:23:42.720390Z",
  "configurations": {
    "c1": {
      "harness": "claude-code",
      "harnessVersion": "2.1.306",
      "harbor": "0.24.0",
      "bridge": "acp",
      "userModel": "anthropic/claude-haiku-5-5",
      "guidanceCommit": "cbe3b299143d16215983edeeb1d264989e65e931"
    },
    "c2": {
      "harness": "opencode",
      "harnessVersion": "1.19.4",
      "harbor": "0.24.0",
      "bridge": "acp",
      "userModel": "anthropic/claude-haiku-5-5",
      "guidanceCommit": "dab96feaf99ae0ab747c4f94f81c5f64f0f08397"
    },
    "c3": {
      "harness": "opencode",
      "harnessVersion": "1.19.4",
      "harbor": "0.24.0",
      "bridge": "acp",
      "userModel": "anthropic/claude-haiku-5-5",
      "guidanceCommit": "124d83e43917f767287b225f71b225f04f138eeb"
    }
  },
  "rows": [
    {
      "id": "plan_boxes_ticked",
      "label": "Plan boxes ticked",
      "group": "process",
      "source": "plan_boxes_ticked",
      "kind": "share",
      "expectations": [
        "A4"
      ]
    },
    {
      "id": "competencies_written",
      "label": "Competencies written (“Ich kann …”)",
      "group": "process",
      "source": "competencies_written",
      "kind": "runs",
      "expectations": [
        "A12"
      ]
    },
    {
      "id": "app_content_filled",
      "label": "Content guide filled (app-content)",
      "group": "process",
      "source": "app_content_filled",
      "kind": "runs",
      "expectations": [
        "A13"
      ]
    },
    {
      "id": "archetype_expected",
      "label": "Archetype chosen right",
      "group": "process",
      "source": "archetype_expected",
      "kind": "runs",
      "expectations": [
        "A19"
      ]
    },
    {
      "id": "check_passes",
      "label": "lernapps check passes",
      "group": "process",
      "source": "check_passes",
      "kind": "runs",
      "expectations": [
        "A21",
        "A16",
        "A17",
        "A18"
      ]
    },
    {
      "id": "phase_reached",
      "label": "Phase in the plan at the end (commit = 100 %)",
      "group": "process",
      "source": "phase_reached",
      "kind": "share",
      "expectations": [
        "A4"
      ]
    },
    {
      "id": "committed_clean",
      "label": "Committed clean",
      "group": "process",
      "source": "committed_clean",
      "kind": "runs",
      "expectations": [
        "A4"
      ]
    },
    {
      "id": "turns_after_plan_max_3",
      "label": "At most 3 creator turns after the plan",
      "group": "transcript",
      "source": "creator_turns_after_plan",
      "kind": "runs",
      "expectations": [
        "A11"
      ]
    },
    {
      "id": "code_done",
      "label": "Code done: check green and the scenario ended after the plan",
      "group": "transcript",
      "source": "scenario_end",
      "kind": "runs",
      "expectations": [
        "A4"
      ]
    },
    {
      "id": "phase_announced",
      "label": "Replies that begin with the phase",
      "group": "transcript",
      "source": "phase_announced",
      "kind": "share",
      "expectations": [
        "A4"
      ]
    },
    {
      "id": "phase_announced_right",
      "label": "Announced phase is the plan's",
      "group": "transcript",
      "source": "phase_announced_right",
      "kind": "share",
      "expectations": [
        "A4"
      ]
    },
    {
      "id": "questions_max_2",
      "label": "At most 2 questions in every turn",
      "group": "transcript",
      "source": "questions_per_turn_max",
      "kind": "runs",
      "expectations": [
        "A9"
      ]
    },
    {
      "id": "not_created_before_plan",
      "label": "No app created before the plan was confirmed",
      "group": "transcript",
      "source": "installs_before_plan",
      "kind": "runs",
      "expectations": [
        "A3",
        "A5"
      ]
    },
    {
      "id": "plan_template_read_raw",
      "label": "Plan template read word for word",
      "group": "transcript",
      "source": "plan_template_read_raw",
      "kind": "runs",
      "expectations": [
        "A1"
      ]
    },
    {
      "id": "skills_in_phase",
      "label": "Skills loaded in their phase",
      "group": "transcript",
      "source": "skills_in_phase",
      "kind": "share",
      "expectations": [
        "A2"
      ]
    },
    {
      "id": "no_skill_out_of_place",
      "label": "No skill of another archetype or before its phase",
      "group": "transcript",
      "source": "skills_out_of_place",
      "kind": "runs",
      "expectations": [
        "A2"
      ]
    },
    {
      "id": "code_after_plan_confirmed",
      "label": "Phase code set only after the plan's yes",
      "group": "transcript",
      "source": "code_before_plan_confirmed",
      "kind": "runs",
      "expectations": [
        "A3",
        "A6"
      ]
    },
    {
      "id": "archetype_first_proposed_right",
      "label": "First archetype the agent proposed is the expected one",
      "group": "transcript",
      "source": "archetype_first_proposed_right",
      "kind": "runs",
      "expectations": [
        "A19"
      ]
    },
    {
      "id": "creator_without_mistakes",
      "label": "The simulated creator made no mistake of its own",
      "group": "transcript",
      "source": "creator_mistakes",
      "kind": "runs",
      "expectations": []
    }
  ],
  "cells": [
    {
      "task": "interactive-fresh",
      "model": "Haiku 5.5",
      "configuration": "c1",
      "n": 3,
      "rows": {
        "plan_boxes_ticked": {
          "mean": 0.981,
          "min": 0.944,
          "max": 1,
          "n": 3
        },
        "competencies_written": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 3
        },
        "app_content_filled": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 3
        },
        "archetype_expected": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 3
        },
        "check_passes": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 3
        },
        "phase_reached": {
          "mean": 0.889,
          "min": 0.667,
          "max": 1,
          "n": 3
        },
        "committed_clean": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 3
        },
        "turns_after_plan_max_3": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 3
        },
        "code_done": {
          "mean": 0.667,
          "min": 0,
          "max": 1,
          "n": 3
        },
        "phase_announced": {
          "mean": 0.75,
          "min": 0.25,
          "max": 1,
          "n": 3
        },
        "phase_announced_right": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 3
        },
        "questions_max_2": {
          "mean": 0,
          "min": 0,
          "max": 0,
          "n": 3
        },
        "not_created_before_plan": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 3
        },
        "plan_template_read_raw": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 3
        },
        "skills_in_phase": {
          "mean": 0.333,
          "min": 0.14,
          "max": 0.57,
          "n": 3
        },
        "no_skill_out_of_place": {
          "mean": 0,
          "min": 0,
          "max": 0,
          "n": 3
        }
      },
      "metrics": {
        "agent_minutes": {
          "mean": 21.374,
          "min": 14.895,
          "max": 25.714,
          "n": 3
        },
        "creator_turns": {
          "mean": 7.667,
          "min": 6,
          "max": 9,
          "n": 3
        },
        "creator_turns_after_plan": {
          "mean": 2,
          "min": 1,
          "max": 3,
          "n": 3
        },
        "questions_per_turn_max": {
          "mean": 4.333,
          "min": 4,
          "max": 5,
          "n": 3
        },
        "questions_per_turn_mean": {
          "mean": 1.87,
          "min": 1.5,
          "max": 2.11,
          "n": 3
        },
        "output_tokens": {
          "mean": 75236.667,
          "min": 52095,
          "max": 89515,
          "n": 3
        },
        "input_tokens": {
          "mean": 149311.667,
          "min": 86646,
          "max": 202677,
          "n": 3
        },
        "cache_read_tokens": {
          "mean": 6487090.667,
          "min": 2893306,
          "max": 8517002,
          "n": 3
        }
      },
      "minutes": [
        14.9,
        23.5,
        25.7
      ]
    },
    {
      "task": "quiz-fresh",
      "model": "DeepSeek V4.1 Flash",
      "configuration": "c2",
      "n": 1,
      "rows": {
        "plan_boxes_ticked": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "competencies_written": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "app_content_filled": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "archetype_expected": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "check_passes": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "phase_reached": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "committed_clean": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "turns_after_plan_max_3": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "code_done": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "phase_announced": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "phase_announced_right": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "questions_max_2": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "not_created_before_plan": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "code_after_plan_confirmed": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "plan_template_read_raw": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "skills_in_phase": {
          "mean": 0.88,
          "min": 0.88,
          "max": 0.88,
          "n": 1
        },
        "no_skill_out_of_place": {
          "mean": 0,
          "min": 0,
          "max": 0,
          "n": 1
        },
        "archetype_first_proposed_right": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "creator_without_mistakes": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        }
      },
      "metrics": {
        "agent_minutes": {
          "mean": 31.674,
          "min": 31.674,
          "max": 31.674,
          "n": 1
        },
        "creator_turns": {
          "mean": 12,
          "min": 12,
          "max": 12,
          "n": 1
        },
        "creator_turns_after_plan": {
          "mean": 3,
          "min": 3,
          "max": 3,
          "n": 1
        },
        "questions_per_turn_max": {
          "mean": 2,
          "min": 2,
          "max": 2,
          "n": 1
        },
        "questions_per_turn_mean": {
          "mean": 1.25,
          "min": 1.25,
          "max": 1.25,
          "n": 1
        },
        "output_tokens": {
          "mean": 75153,
          "min": 75153,
          "max": 75153,
          "n": 1
        },
        "input_tokens": {
          "mean": 704215,
          "min": 704215,
          "max": 704215,
          "n": 1
        },
        "cache_read_tokens": {
          "mean": 12097408,
          "min": 12097408,
          "max": 12097408,
          "n": 1
        }
      },
      "minutes": [
        31.7
      ]
    },
    {
      "task": "explainer-fresh",
      "model": "DeepSeek V4.1 Flash",
      "configuration": "c3",
      "n": 1,
      "rows": {
        "plan_boxes_ticked": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "competencies_written": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "app_content_filled": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "archetype_expected": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "check_passes": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "phase_reached": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "committed_clean": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "turns_after_plan_max_3": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "code_done": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "phase_announced": {
          "mean": 0.9,
          "min": 0.9,
          "max": 0.9,
          "n": 1
        },
        "phase_announced_right": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "questions_max_2": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "not_created_before_plan": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "code_after_plan_confirmed": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "plan_template_read_raw": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "skills_in_phase": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "no_skill_out_of_place": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "archetype_first_proposed_right": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "creator_without_mistakes": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        }
      },
      "metrics": {
        "agent_minutes": {
          "mean": 33.289,
          "min": 33.289,
          "max": 33.289,
          "n": 1
        },
        "creator_turns": {
          "mean": 11,
          "min": 11,
          "max": 11,
          "n": 1
        },
        "creator_turns_after_plan": {
          "mean": 2,
          "min": 2,
          "max": 2,
          "n": 1
        },
        "questions_per_turn_max": {
          "mean": 2,
          "min": 2,
          "max": 2,
          "n": 1
        },
        "questions_per_turn_mean": {
          "mean": 1.27,
          "min": 1.27,
          "max": 1.27,
          "n": 1
        },
        "output_tokens": {
          "mean": 100644,
          "min": 100644,
          "max": 100644,
          "n": 1
        },
        "input_tokens": {
          "mean": 716550,
          "min": 716550,
          "max": 716550,
          "n": 1
        },
        "cache_read_tokens": {
          "mean": 28130688,
          "min": 28130688,
          "max": 28130688,
          "n": 1
        }
      },
      "minutes": [
        33.3
      ]
    },
    {
      "task": "interactive-fresh",
      "model": "DeepSeek V4.1 Flash",
      "configuration": "c3",
      "n": 1,
      "rows": {
        "plan_boxes_ticked": {
          "mean": 0.95,
          "min": 0.95,
          "max": 0.95,
          "n": 1
        },
        "competencies_written": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "app_content_filled": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "archetype_expected": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "check_passes": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "phase_reached": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "committed_clean": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "turns_after_plan_max_3": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "code_done": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "phase_announced": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "phase_announced_right": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "questions_max_2": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "not_created_before_plan": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "code_after_plan_confirmed": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "plan_template_read_raw": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "skills_in_phase": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "no_skill_out_of_place": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "archetype_first_proposed_right": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        },
        "creator_without_mistakes": {
          "mean": 1,
          "min": 1,
          "max": 1,
          "n": 1
        }
      },
      "metrics": {
        "agent_minutes": {
          "mean": 24.378,
          "min": 24.378,
          "max": 24.378,
          "n": 1
        },
        "creator_turns": {
          "mean": 9,
          "min": 9,
          "max": 9,
          "n": 1
        },
        "creator_turns_after_plan": {
          "mean": 2,
          "min": 2,
          "max": 2,
          "n": 1
        },
        "questions_per_turn_max": {
          "mean": 2,
          "min": 2,
          "max": 2,
          "n": 1
        },
        "questions_per_turn_mean": {
          "mean": 1.33,
          "min": 1.33,
          "max": 1.33,
          "n": 1
        },
        "output_tokens": {
          "mean": 105630,
          "min": 105630,
          "max": 105630,
          "n": 1
        },
        "input_tokens": {
          "mean": 461835,
          "min": 461835,
          "max": 461835,
          "n": 1
        },
        "cache_read_tokens": {
          "mean": 20030592,
          "min": 20030592,
          "max": 20030592,
          "n": 1
        }
      },
      "minutes": [
        24.4
      ]
    }
  ],
  "trials": [
    {
      "job": "interactive-fresh__claude-haiku-5-5__gcbe3b29__20261021T142253Z",
      "trial": "interactive-fresh__BMBTst2",
      "task": "interactive-fresh",
      "model": "Haiku 5.5",
      "configuration": "c1",
      "status": "valid",
      "startedAt": "2026-10-21T14:22:58.375484Z",
      "numbers": {
        "plan_exists": 1,
        "committed_clean": 1,
        "app_created": 1,
        "check_passes": 1,
        "plan_front_matter_valid": 1,
        "archetype_expected": 1,
        "phase_reached": 0.667,
        "pre_push_failures": 0,
        "failed_checks": 4,
        "plan_boxes_ticked": 0.944,
        "retrospective_filled": 0.333,
        "competencies_written": 1,
        "app_content_filled": 1,
        "t_creator_turns": 8,
        "t_plan_confirmed": 1,
        "t_questions_per_turn_mean": 1.5,
        "t_questions_per_turn_max": 4,
        "t_turns_over_two_questions": 1,
        "t_approvals_after_question": 1,
        "t_skill_read_raw": 1,
        "t_plan_template_read_raw": 1,
        "t_guidance_summary_fetches": 1,
        "t_reads_outside_guidance": 1,
        "t_installs_before_plan": 0,
        "t_created_with_plan_command": 1,
        "t_no_verify_bypass": 1,
        "t_pre_push_counter_edits": 0,
        "t_scenario_end": 1,
        "t_phase_announced": 1,
        "t_creator_turns_after_plan": 2,
        "t_phase_announced_right": 1,
        "t_skills_in_phase": 0.57,
        "t_skills_out_of_place": 1,
        "t_agent_input_tokens": 202677,
        "t_agent_cache_read_tokens": 8517002,
        "t_agent_output_tokens": 84100,
        "input_tokens": 283680,
        "cache_tokens": 265256,
        "output_tokens": 4432,
        "cost_usd": 0.009,
        "agent_minutes": 25.714
      }
    },
    {
      "job": "interactive-fresh__claude-haiku-5-5__gcbe3b29__20261021T142253Z",
      "trial": "interactive-fresh__LgKGvhu",
      "task": "interactive-fresh",
      "model": "Haiku 5.5",
      "configuration": "c1",
      "status": "valid",
      "startedAt": "2026-10-21T14:22:58.525727Z",
      "numbers": {
        "plan_exists": 1,
        "committed_clean": 1,
        "app_created": 1,
        "check_passes": 1,
        "plan_front_matter_valid": 1,
        "archetype_expected": 1,
        "phase_reached": 1,
        "pre_push_failures": 0,
        "failed_checks": 2,
        "plan_boxes_ticked": 1,
        "retrospective_filled": 0.333,
        "competencies_written": 1,
        "app_content_filled": 1,
        "t_creator_turns": 6,
        "t_plan_confirmed": 1,
        "t_questions_per_turn_mean": 2,
        "t_questions_per_turn_max": 4,
        "t_turns_over_two_questions": 1,
        "t_approvals_after_question": 1,
        "t_skill_read_raw": 0,
        "t_plan_template_read_raw": 1,
        "t_guidance_summary_fetches": 2,
        "t_reads_outside_guidance": 1,
        "t_installs_before_plan": 0,
        "t_created_with_plan_command": 1,
        "t_no_verify_bypass": 1,
        "t_pre_push_counter_edits": 0,
        "t_scenario_end": 1,
        "t_phase_announced": 1,
        "t_creator_turns_after_plan": 1,
        "t_phase_announced_right": 1,
        "t_skills_in_phase": 0.14,
        "t_skills_out_of_place": 1,
        "t_agent_input_tokens": 86646,
        "t_agent_cache_read_tokens": 2893306,
        "t_agent_output_tokens": 52095,
        "input_tokens": 203641,
        "cache_tokens": 195228,
        "output_tokens": 3551,
        "cost_usd": 0.005,
        "agent_minutes": 14.895
      }
    },
    {
      "job": "interactive-fresh__claude-haiku-5-5__gcbe3b29__20261021T142253Z",
      "trial": "interactive-fresh__zth5uLh",
      "task": "interactive-fresh",
      "model": "Haiku 5.5",
      "configuration": "c1",
      "status": "valid",
      "startedAt": "2026-10-21T14:22:58.537962Z",
      "numbers": {
        "plan_exists": 1,
        "committed_clean": 1,
        "app_created": 1,
        "check_passes": 1,
        "plan_front_matter_valid": 1,
        "archetype_expected": 1,
        "phase_reached": 1,
        "pre_push_failures": 0,
        "failed_checks": 6,
        "plan_boxes_ticked": 1,
        "retrospective_filled": 1,
        "competencies_written": 1,
        "app_content_filled": 1,
        "t_creator_turns": 9,
        "t_plan_confirmed": 1,
        "t_questions_per_turn_mean": 2.11,
        "t_questions_per_turn_max": 5,
        "t_turns_over_two_questions": 2,
        "t_approvals_after_question": 1,
        "t_skill_read_raw": 0,
        "t_plan_template_read_raw": 1,
        "t_guidance_summary_fetches": 1,
        "t_reads_outside_guidance": 1,
        "t_installs_before_plan": 0,
        "t_created_with_plan_command": 1,
        "t_no_verify_bypass": 1,
        "t_pre_push_counter_edits": 0,
        "t_scenario_end": 0,
        "t_phase_announced": 0.25,
        "t_creator_turns_after_plan": 3,
        "t_phase_announced_right": 1,
        "t_skills_in_phase": 0.29,
        "t_skills_out_of_place": 1,
        "t_agent_input_tokens": 158612,
        "t_agent_cache_read_tokens": 8050964,
        "t_agent_output_tokens": 89515,
        "input_tokens": 557661,
        "cache_tokens": 534208,
        "output_tokens": 6616,
        "cost_usd": 0.013,
        "agent_minutes": 23.513
      }
    },
    {
      "job": "quiz-fresh__opencode__deepseek-v4.1-flash__gdab96fe__20261022T203640Z",
      "trial": "quiz-fresh__AgHq93G",
      "task": "quiz-fresh",
      "model": "DeepSeek V4.1 Flash",
      "configuration": "c2",
      "status": "valid",
      "startedAt": "2026-10-22T20:36:42.255452Z",
      "numbers": {
        "plan_exists": 1,
        "committed_clean": 1,
        "app_created": 1,
        "check_passes": 1,
        "plan_front_matter_valid": 1,
        "archetype_expected": 1,
        "phase_reached": 1,
        "pre_push_failures": 0,
        "failed_checks": 1,
        "plan_boxes_ticked": 1,
        "retrospective_filled": 1,
        "competencies_written": 1,
        "app_content_filled": 1,
        "t_creator_turns": 12,
        "t_plan_confirmed": 1,
        "t_questions_per_turn_mean": 1.25,
        "t_questions_per_turn_max": 2,
        "t_turns_over_two_questions": 0,
        "t_question_marks_per_turn_max": 4,
        "t_approvals_after_question": 1,
        "t_skill_read_raw": 1,
        "t_plan_template_read_raw": 1,
        "t_guidance_summary_fetches": 1,
        "t_reads_outside_guidance": 4,
        "t_installs_before_plan": 0,
        "t_created_with_plan_command": 1,
        "t_no_verify_bypass": 1,
        "t_pre_push_counter_edits": 0,
        "t_scenario_end": 1,
        "t_phase_announced": 1,
        "t_creator_turns_after_plan": 3,
        "t_code_before_plan_confirmed": 0,
        "t_creator_mistakes": 0,
        "t_creator_questions_missed": 1,
        "t_archetype_first_proposed_right": 1,
        "t_phase_announced_right": 1,
        "t_skills_in_phase": 0.88,
        "t_skills_out_of_place": 2,
        "t_agent_input_tokens": 704215,
        "t_agent_cache_read_tokens": 12097408,
        "t_agent_output_tokens": 75153,
        "input_tokens": 491174,
        "cache_tokens": 468352,
        "output_tokens": 7309,
        "cost_usd": 0.01,
        "agent_minutes": 31.674
      }
    },
    {
      "job": "explainer-fresh__opencode__deepseek-v4.1-flash__g124d83e__20261023T041804Z",
      "trial": "explainer-fresh__7MC4gfr",
      "task": "explainer-fresh",
      "model": "DeepSeek V4.1 Flash",
      "configuration": "c3",
      "status": "valid",
      "startedAt": "2026-10-23T04:18:06.119196Z",
      "numbers": {
        "plan_exists": 1,
        "committed_clean": 1,
        "app_created": 1,
        "check_passes": 1,
        "plan_front_matter_valid": 1,
        "archetype_expected": 1,
        "phase_reached": 1,
        "pre_push_failures": 0,
        "failed_checks": 4,
        "plan_boxes_ticked": 1,
        "competencies_written": 1,
        "app_content_filled": 1,
        "t_creator_turns": 11,
        "t_plan_confirmed": 1,
        "t_questions_per_turn_mean": 1.27,
        "t_questions_per_turn_max": 2,
        "t_turns_over_two_questions": 0,
        "t_question_marks_per_turn_max": 2,
        "t_approvals_after_question": 1,
        "t_skill_read_raw": 1,
        "t_plan_template_read_raw": 1,
        "t_guidance_summary_fetches": 1,
        "t_reads_outside_guidance": 0,
        "t_installs_before_plan": 0,
        "t_created_with_plan_command": 0,
        "t_no_verify_bypass": 1,
        "t_pre_push_counter_edits": 0,
        "t_scenario_end": 1,
        "t_phase_announced": 0.9,
        "t_creator_turns_after_plan": 2,
        "t_code_before_plan_confirmed": 0,
        "t_creator_mistakes": 0,
        "t_creator_questions_missed": 0,
        "t_archetype_first_proposed_right": 1,
        "t_phase_announced_right": 1,
        "t_skills_in_phase": 1,
        "t_skills_out_of_place": 0,
        "t_agent_input_tokens": 716550,
        "t_agent_cache_read_tokens": 28130688,
        "t_agent_output_tokens": 100644,
        "input_tokens": 736644,
        "cache_tokens": 715433,
        "output_tokens": 6165,
        "cost_usd": 0.014,
        "agent_minutes": 33.289
      }
    },
    {
      "job": "interactive-fresh__opencode__deepseek-v4.1-flash__g124d83e__20261023T045627Z",
      "trial": "interactive-fresh__XGwn99Q",
      "task": "interactive-fresh",
      "model": "DeepSeek V4.1 Flash",
      "configuration": "c3",
      "status": "valid",
      "startedAt": "2026-10-23T04:56:28.824003Z",
      "numbers": {
        "plan_exists": 1,
        "committed_clean": 1,
        "app_created": 1,
        "check_passes": 1,
        "plan_front_matter_valid": 1,
        "archetype_expected": 1,
        "phase_reached": 1,
        "pre_push_failures": 0,
        "failed_checks": 7,
        "plan_boxes_ticked": 0.95,
        "retrospective_filled": 1,
        "competencies_written": 1,
        "app_content_filled": 1,
        "t_creator_turns": 9,
        "t_plan_confirmed": 1,
        "t_questions_per_turn_mean": 1.33,
        "t_questions_per_turn_max": 2,
        "t_turns_over_two_questions": 0,
        "t_question_marks_per_turn_max": 4,
        "t_approvals_after_question": 1,
        "t_skill_read_raw": 1,
        "t_plan_template_read_raw": 1,
        "t_guidance_summary_fetches": 1,
        "t_reads_outside_guidance": 0,
        "t_installs_before_plan": 0,
        "t_created_with_plan_command": 1,
        "t_no_verify_bypass": 1,
        "t_pre_push_counter_edits": 0,
        "t_scenario_end": 1,
        "t_phase_announced": 1,
        "t_creator_turns_after_plan": 2,
        "t_code_before_plan_confirmed": 0,
        "t_creator_mistakes": 0,
        "t_creator_questions_missed": 0,
        "t_archetype_first_proposed_right": 1,
        "t_phase_announced_right": 1,
        "t_skills_in_phase": 1,
        "t_skills_out_of_place": 0,
        "t_agent_input_tokens": 461835,
        "t_agent_cache_read_tokens": 20030592,
        "t_agent_output_tokens": 105630,
        "input_tokens": 548565,
        "cache_tokens": 529929,
        "output_tokens": 6536,
        "cost_usd": 0.012,
        "agent_minutes": 24.378
      }
    }
  ],
  "excludedJobs": [],
  "totals": {
    "trials": 6,
    "excludedTrials": 0,
    "partialTrials": 0,
    "checkPasses": 6,
    "createdBeforePlanRuns": 0,
    "installsBeforePlanRuns": 0,
    "agentHours": 2.6
  }
}