# eval.view.yaml — agentic-eval-harness eval-dashboard, re-expressed as a
# inkSpec VIEW spec. Compiles (with the harness data bundle) to a
# self-contained eval-dashboard.html that renders identically to the original.
kind: view
x-forge-name: eval-dashboard
title: "agentic-eval-harness"
adapters: [eval-scoring]
footer: "Renders <a href=\"https://github.com/chris-youngblut-solutions/agentic-eval-harness\">agentic-eval-harness</a> JSON (scorecards + transcripts). The harness is the source of truth for all metrics and scoring."
views:
  - key: overview
    label: "Overview"
    select: {domain: true, run: after, case: false}
    widgets:
      - widget: heading
        value: "$domain"
      - widget: chips
        source: card
        fields: [run_id, backend, model]
      - widget: stat-cards
        cards:
          - value: "eval-scoring.passedCount(card)"
            denom: "{card.cases.length}"
            label: "cases passed"
          - value: "eval-scoring.totalScore(card)"
            denom: "{card.cases.length}"
            label: "total score"
      - widget: hard-gate-banner
        source: "eval-scoring.hardGateFailures(card)"
      - widget: metric-rollup
        source: "eval-scoring.byMetric(card)"
      - widget: case-table
        source: card
  - key: diff
    label: "Regression diff"
    select: {domain: true, run: both, case: false}
    widgets:
      - widget: heading
        value: "Regression diff"
      - widget: regression-diff
        before: before
        after: after
  - key: transcript
    label: "Transcript"
    select: {domain: true, run: after, case: true}
    widgets:
      - widget: heading
        value: "Transcript"
      - widget: transcript
        source: transcript
  - key: cross
    label: "Cross-domain"
    select: {domain: false, run: false, case: false}
    widgets:
      - widget: heading
        value: "Cross-domain"
      - widget: caption
        text: "Latest run per domain — one engine, N domains."
      - widget: cross-grid
  - key: trend
    label: "Trend"
    select: {domain: true, run: false, case: false}
    widgets:
      - widget: heading
        value: "$domain"
      - widget: caption
        text: "Total score across this domain's runs — oldest to newest."
      - widget: trend
        source: "eval-scoring.scoreTrend(dataset, domain)"
        caption: "score over runs"