WIP: checkpoint before stage-3 sub-stage rewrite

data-pipeline/db/reset.ts

@@ -0,0 +1,41 @@
+import path from "node:path";
+import { fileURLToPath } from "node:url";
+import Database from "better-sqlite3";
+
+// ── Paths ─────────────────────────────────────────────────────────────────────
+
+const __dirname = path.dirname(fileURLToPath(import.meta.url));
+const DB_PATH = path.join(__dirname, "pipeline.db");
+
+// ── Main ──────────────────────────────────────────────────────────────────────
+
+function main(): void {
+  const mode = process.argv[2];
+
+  if (!mode || (mode !== "round1" && mode !== "all")) {
+    console.error("Usage: pnpm db:reset round1 | all");
+    console.error("  round1 — delete all round1 sub-stage rows");
+    console.error("  all    — delete all run_status rows except reverse_link");
+    process.exit(1);
+  }
+
+  const db = new Database(DB_PATH);
+
+  let result: { changes: number };
+
+  if (mode === "round1") {
+    result = db
+      .prepare("DELETE FROM run_status WHERE stage LIKE 'round1%'")
+      .run();
+    console.log(`Deleted ${result.changes} round1 rows from run_status`);
+  } else {
+    result = db
+      .prepare("DELETE FROM run_status WHERE stage NOT IN ('reverse_link')")
+      .run();
+    console.log(`Deleted ${result.changes} rows from run_status`);
+  }
+
+  db.close();
+}
+
+main();

data-pipeline/package.json

@@ -4,11 +4,11 @@
   "private": true,
   "type": "module",
   "scripts": {
+    "db:reset": "tsx db/reset.ts",
     "extract": "tsx stage-1-extract/scripts/extract.ts",
     "reverse-link": "tsx stage-2-reverse-link/scripts/reverse-link.ts",
     "db:import": "tsx db/import.ts",
     "db:init": "tsx db/init.ts",
-    "annotate": "tsx stage-2-annotate/scripts/annotate.ts",
     "test": "vitest run",
     "test:watch": "vitest",
     "pipeline:run": "tsx --env-file .env pipeline.ts"

data-pipeline/pipeline.ts

@@ -110,7 +110,7 @@ async function checkProviderReady(provider: ProviderConfig): Promise<void> {
 async function generateRunName(): Promise<string> {
   await fs.mkdir(PATHS.reports, { recursive: true });
 
-  const date = new Date().toISOString().slice(0, 10);
+  const date = new Date().toISOString().exi(0, 10);
   const files = await fs.readdir(PATHS.reports);
   const todaysRuns = files.filter(
     (f) => f.startsWith(date) && f.endsWith(".json"),
@@ -175,7 +175,8 @@ function getModelRound1Status(modelName: string): StageStatus {
     db
       .prepare(
         `SELECT COUNT(*) as count FROM run_status
-         WHERE model_name = ? AND stage = 'round1' AND status = 'complete'`,
+         WHERE model_name = ? AND stage = 'round1_gloss'
+         AND status = 'complete'`,
       )
       .get(modelName) as { count: number }
   ).count;
@@ -602,9 +603,9 @@ async function main(): Promise<void> {
     runCompare();
   }
 
-  // ── Report
-  stats.stoppedAt = new Date();
-  await generateReport(runName, stats);
+  // ── Report (disabled until full pipeline is implemented)
+  // stats.stoppedAt = new Date();
+  // await generateReport(runName, stats);
 
   console.log("\nPipeline complete.");
 }