feat(labs): PDF upload, text extraction, LLM draft pipeline

server/src/routes/labs.ts

@@ -0,0 +1,68 @@
+import { desc, eq } from "drizzle-orm";
+import { Hono } from "hono";
+import { randomUUID } from "node:crypto";
+import { mkdirSync } from "node:fs";
+import { join } from "node:path";
+import type { Db } from "../db";
+import { labDrafts } from "../db/schema";
+import { extractFromText } from "../lib/extract";
+import { pdfToText } from "../lib/pdf";
+
+export type LabsDeps = { db: Db; key: Buffer; dataDir: string; llmFetch?: typeof fetch };
+
+const MAX_UPLOAD = 15 * 1024 * 1024;
+
+export function labsRoutes(deps: LabsDeps) {
+  const app = new Hono();
+
+  app.post("/labs/upload", async (c) => {
+    const body = await c.req.parseBody();
+    const file = body.file;
+    if (!(file instanceof File)) return c.json({ error: "file field required" }, 400);
+    if (!file.name.toLowerCase().endsWith(".pdf") && file.type !== "application/pdf") {
+      return c.json({ error: "not_a_pdf" }, 400);
+    }
+    if (file.size > MAX_UPLOAD) return c.json({ error: "too_large" }, 400);
+
+    const id = randomUUID();
+    const uploadsDir = join(deps.dataDir, "uploads");
+    mkdirSync(uploadsDir, { recursive: true });
+    const filePath = join(uploadsDir, `${id}.pdf`);
+    const bytes = new Uint8Array(await file.arrayBuffer());
+    await Bun.write(filePath, bytes);
+
+    // Extraction failures land on the draft row so the user sees them in the
+    // review UI instead of the upload 500ing.
+    let extracted: string | null = null;
+    let error: string | null = null;
+    try {
+      const text = await pdfToText(bytes);
+      if (text.trim().length < 20) throw new Error("pdf_error: no text layer (scanned PDFs are not supported yet)");
+      const draft = await extractFromText({ db: deps.db, key: deps.key, fetchImpl: deps.llmFetch }, text);
+      extracted = JSON.stringify(draft);
+    } catch (e) {
+      error = e instanceof Error ? e.message : "extraction failed";
+    }
+
+    await deps.db.insert(labDrafts).values({
+      id, filename: file.name, filePath, status: "pending", extracted, error, createdAt: Date.now(),
+    });
+    return c.json({ id }, 201);
+  });
+
+  app.get("/labs/drafts", async (c) => {
+    const rows = await deps.db.select().from(labDrafts).orderBy(desc(labDrafts.createdAt));
+    return c.json({
+      drafts: rows.map((r) => ({
+        id: r.id,
+        filename: r.filename,
+        status: r.status,
+        error: r.error,
+        markerCount: r.extracted ? (JSON.parse(r.extracted).markers?.length ?? 0) : 0,
+        createdAt: r.createdAt,
+      })),
+    });
+  });
+
+  return app;
+}