{
  "id": "eval-harness/html-report-for-eval-runs",
  "slug": "html-report-for-eval-runs",
  "title": "Session: html-report-for-eval-runs — 2026-10-30",
  "type": "source",
  "project": "eval-harness",
  "date": "2026-10-30",
  "started": "2026-10-30T14:10:00+00:00",
  "ended": "2026-10-30T15:46:00+00:00",
  "model": "gpt-5-codex",
  "cwd": "/home/dev/code/eval-harness",
  "git_branch": "feat/html-report",
  "permission_mode": "default",
  "user_messages": 1,
  "tool_calls": 3,
  "tools_used": [
    "Bash",
    "Write"
  ],
  "is_subagent": false,
  "wikilinks_out": [
    "RegressionTracking",
    "Reporting",
    "eval-harness"
  ],
  "body_text": "Project: eval-harness · Branch: feat/html-report · Mode: default · Model: gpt-5-codex\n\nSummary\n\nGenerated a self-contained HTML report per eval run: summary table, per-metric distributions, a diff view against the previous run, and drill-down into failing cases with judge rationales.\n\nConversation\n\nTurn 1 — User\n\nGive me a report I can share, comparing this run with the last one.\n\nTurn 1 — Assistant\n\nSingle HTML file with inline CSS/JS, metrics summary, histogram per metric, regressions highlighted against the baseline run, and expandable failing cases.\n\nTools used in this turn:\n\n- Write: harness/report/html.py\n- Write: harness/report/template.html\n- Bash: python -m harness report runs/latest --baseline runs/prev — report.html\n\nConnections\n\n- eval-harness\n- Reporting\n- RegressionTracking",
  "sha256": "eed2775523e06df9",
  "source_url": "sessions/eval-harness/2026-10-30-html-report-for-eval-runs.html"
}