herm

apps/web/scripts/fill-training-dataset.ts

@@ -667,11 +667,23 @@ function scanDataset(): ScanResult {
   return { diseaseCounts, healthyCount };
 }
 
+// ─── CLI Flags ──────────────────────────────────────────────────────────────
+
+function parseFlags(): { reverse: boolean } {
+  const args = process.argv.slice(2);
+  return {
+    reverse: args.includes("--reverse") || args.includes("-r"),
+  };
+}
+
 // ─── Main ───────────────────────────────────────────────────────────────────
 
 async function main() {
+  const flags = parseFlags();
+
   console.log("=".repeat(60));
   console.log("TRAINING DATASET FILL — Parallelized gap-filling download");
+  if (flags.reverse) console.log("  (reverse order — processing from lowest deficit first)");
   console.log("=".repeat(60));
 
   // Ensure dataset directory exists
@@ -717,6 +729,10 @@ async function main() {
   // Sort by deficit size (largest first) so we prioritize the neediest diseases
   deficits.sort((a, b) => b.needed - a.needed);
 
+  // Reverse order if --reverse/-r flag is set (useful to try a different
+  // direction when the front of the queue keeps hitting dead URLs)
+  if (flags.reverse) deficits.reverse();
+
   const healthyDeficit = TARGET_HEALTHY - healthyCount;
 
   console.log(`\n${"=".repeat(60)}`);
@@ -727,6 +743,9 @@ async function main() {
   console.log(`  Healthy deficit:        ${Math.max(0, healthyDeficit)}`);
   console.log(`  Parallelism:            ${DISEASE_CONCURRENCY} diseases at once`);
   console.log(`  DDG rate limit:         ${DDG_RATE_LIMIT_RPS} req/s (shared)`);
+  console.log(
+    `  Order:                  ${flags.reverse ? "reverse (--reverse)" : "normal (deficit-first)"}`,
+  );
   console.log(`${"=".repeat(60)}`);
 
   if (deficits.length === 0 && healthyDeficit <= 0) {