feat: add pipeline orchestrator skeleton with startup checks, stage runners, shutdown handler, and report generation

data-pipeline/db/import.ts

@@ -216,7 +216,9 @@ async function main(): Promise<void> {
   await importStage2();
 }
 
-main().catch((err) => {
-  console.error(err);
-  process.exit(1);
-});
+if (import.meta.url === `file://${process.argv[1]}`) {
+  main().catch((err) => {
+    console.error(err);
+    process.exit(1);
+  });
+}

data-pipeline/db/init.ts

@@ -33,7 +33,10 @@ async function main(): Promise<void> {
   await initDb();
 }
 
-main().catch((err) => {
-  console.error(err);
-  process.exit(1);
-});
+// after
+if (import.meta.url === `file://${process.argv[1]}`) {
+  main().catch((err) => {
+    console.error(err);
+    process.exit(1);
+  });
+}

data-pipeline/db/schema.sql

@@ -41,7 +41,16 @@ CREATE TABLE IF NOT EXISTS cefr_source_votes (
 -- stage:  round1 | round2 | tiebreak
 -- status: pending | complete | needs_review | flagged
 
-
+CREATE TABLE IF NOT EXISTS run_status (
+  id         INTEGER PRIMARY KEY,
+  source_id  TEXT    NOT NULL,
+  model_name TEXT    NOT NULL,
+  stage      TEXT    NOT NULL,
+  status     TEXT    NOT NULL,
+  created_at TEXT    NOT NULL DEFAULT (datetime('now')),
+  updated_at TEXT    NOT NULL DEFAULT (datetime('now')),
+  UNIQUE (source_id, model_name, stage)
+);
 
 -- ── Round 1 output ────────────────────────────────────────────────────────────
 -- One row per translation/language per model. Written atomically per record.