Function classifyTaskMoves

bench/diff.js:137–149

(base, feat)

//   have one attempt per task in the current harness, so soft == hard for now.

function classifyTaskMoves(base, feat) {
  const hard = []; // baseline pass → feature fail
  const recovered = []; // baseline fail → feature pass
  const allIds = new Set([...Object.keys(base.byId), ...Object.keys(feat.byId)]);
  for (const id of allIds) {
    const b = base.byId[id];
    const f = feat.byId[id];
    if (!b || !f) continue; // task added or removed — skip silently
    if (b.passed && !f.passed) hard.push(id);
    if (!b.passed && f.passed) recovered.push(id);
  }
  return { hard, recovered };
}

// ─── rendering ───────────────────────────────────────────────────────────────