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

bun.lock

@@ -15,6 +15,7 @@
         "@helios/shared": "workspace:*",
         "drizzle-orm": "^0.44.0",
         "hono": "^4.6.0",
+        "unpdf": "^1.8.1",
         "zod": "^3.24.0",
       },
       "devDependencies": {
@@ -322,6 +323,8 @@
 
     "undici-types": ["undici-types@8.3.0", "", {}, "sha512-j375ScV60dom+YkPFIfTLcOiPxkN/buHz5GobjLhixFuANaNs3C9l4GmrWqejgXWJ7BbJcFYpTEUkS1Ge8bpZQ=="],
 
+    "unpdf": ["unpdf@1.8.1", "", { "peerDependencies": { "@napi-rs/canvas": "^0.1.69 || ^1.0.0" }, "optionalPeers": ["@napi-rs/canvas"] }, "sha512-xkURhy2SoGpOIH0a1gLHNkASPIQYonadDJs2AQwPEfUakafeD9EA1WTWWsaR++gfTCXJpV27W7tU1nXuk82UKQ=="],
+
     "update-browserslist-db": ["update-browserslist-db@1.3.1", "", { "dependencies": { "escalade": "^3.2.0", "picocolors": "^1.1.1" }, "peerDependencies": { "browserslist": ">= 4.21.0" }, "bin": { "update-browserslist-db": "cli.js" } }, "sha512-ZZ61DsRsOnakl74HAmp3oSN4aXUmEWXf+i/yv0h7tIBfICc3VdrFErQKUUKPgu3AMsTUMbcongALEN4l6GSUrQ=="],
 
     "vite": ["vite@6.4.3", "", { "dependencies": { "esbuild": "^0.25.0", "fdir": "^6.4.4", "picomatch": "^4.0.2", "postcss": "^8.5.3", "rollup": "^4.34.9", "tinyglobby": "^0.2.13" }, "optionalDependencies": { "fsevents": "~2.3.3" }, "peerDependencies": { "@types/node": "^18.0.0 || ^20.0.0 || >=22.0.0", "jiti": ">=1.21.0", "less": "*", "lightningcss": "^1.21.0", "sass": "*", "sass-embedded": "*", "stylus": "*", "sugarss": "*", "terser": "^5.16.0", "tsx": "^4.8.1", "yaml": "^2.4.2" }, "optionalPeers": ["@types/node", "jiti", "less", "lightningcss", "sass", "sass-embedded", "stylus", "sugarss", "terser", "tsx", "yaml"], "bin": { "vite": "bin/vite.js" } }, "sha512-NTKlcQjlAK7MlQoyb6LgaqHc8sso/pVyUJYWMws3jg21uTJw/LddqIFPcPqP6PzpgbIcZyKI85sFE4HBrQDA8A=="],

server/package.json

@@ -5,7 +5,11 @@
     "@helios/shared": "workspace:*",
     "drizzle-orm": "^0.44.0",
     "hono": "^4.6.0",
+    "unpdf": "^1.8.1",
     "zod": "^3.24.0"
   },
-  "devDependencies": { "bun-types": "latest", "drizzle-kit": "^0.31.0" }
+  "devDependencies": {
+    "bun-types": "latest",
+    "drizzle-kit": "^0.31.0"
+  }
 }

server/src/app.ts

@@ -3,9 +3,10 @@ import { getCookie } from "hono/cookie";
 import { serveStatic } from "hono/bun";
 import type { Db } from "./db";
 import { authRoutes, isAuthenticated } from "./routes/auth";
+import { labsRoutes } from "./routes/labs";
 import { settingsRoutes } from "./routes/settings";
 
-export type Deps = { db: Db; key: Buffer };
+export type Deps = { db: Db; key: Buffer; dataDir: string; llmFetch?: typeof fetch };
 const PUBLIC = new Set(["/api/health", "/api/me", "/api/setup", "/api/login"]);
 
 export function createApp(deps: Deps) {
@@ -20,6 +21,7 @@ export function createApp(deps: Deps) {
   });
   app.route("/api", authRoutes({ db: deps.db }));
   app.route("/api", settingsRoutes(deps));
+  app.route("/api", labsRoutes(deps));
   // Later route groups (connectors, chat) mount here.
   app.all("/api/*", (c) => c.json({ error: "not found" }, 404));
   app.use("/*", serveStatic({ root: "./web/dist" }));

server/src/index.ts

@@ -3,6 +3,6 @@ import { loadOrCreateKey } from "./lib/crypto";
 import { createApp } from "./app";
 
 const dataDir = process.env.DATA_DIR ?? "./data";
-const app = createApp({ db: openDb(dataDir), key: loadOrCreateKey(dataDir) });
+const app = createApp({ db: openDb(dataDir), key: loadOrCreateKey(dataDir), dataDir });
 
 export default { port: Number(process.env.PORT ?? 3000), fetch: app.fetch };

server/src/lib/extract.ts

@@ -0,0 +1,15 @@
+import { ExtractedDraft } from "@helios/shared";
+import { chatJSON, type LlmDeps } from "./llm";
+
+const SYSTEM = `You extract structured blood-test results from the raw text of a lab report.
+Return ONLY a JSON object: {"collectedDate": "YYYY-MM-DD" or null, "labName": string or null, "markers": [{"panel": string or null, "name": string, "value": string, "unit": string or null, "referenceRange": string or null, "flagged": boolean}]}.
+Rules: copy names, values, units, and reference ranges EXACTLY as printed — do not convert units or round values. "value" is always a string (keep comparators like "<0.3"). Set "flagged" true only when the report marks the result abnormal (H, L, *, bold, out-of-range annotation). Use the specimen collection date, not the report date. Skip commentary, footers, and reference-only rows with no result.`;
+
+const MAX_CHARS = 40_000;
+
+export async function extractFromText(deps: LlmDeps, text: string): Promise<ExtractedDraft> {
+  const out = await chatJSON(deps, { system: SYSTEM, user: text.slice(0, MAX_CHARS) });
+  const parsed = ExtractedDraft.safeParse(out);
+  if (!parsed.success) throw new Error("llm_error: draft failed schema validation");
+  return parsed.data;
+}

server/src/lib/pdf.ts

@@ -0,0 +1,7 @@
+import { extractText, getDocumentProxy } from "unpdf";
+
+export async function pdfToText(data: Uint8Array): Promise<string> {
+  const doc = await getDocumentProxy(data);
+  const { text } = await extractText(doc, { mergePages: true });
+  return text;
+}

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;
+}

server/test/auth.test.ts

@@ -8,7 +8,7 @@ import { loadOrCreateKey } from "../src/lib/crypto";
 
 function makeApp() {
   const dir = mkdtempSync(join(tmpdir(), "helios-"));
-  return createApp({ db: openDb(dir), key: loadOrCreateKey(dir) });
+  return createApp({ db: openDb(dir), key: loadOrCreateKey(dir), dataDir: dir });
 }
 const json = (body: unknown) => ({
   method: "POST",

server/test/extract.test.ts

@@ -0,0 +1,46 @@
+import { describe, expect, test } from "bun:test";
+import { mkdtempSync } from "node:fs";
+import { tmpdir } from "node:os";
+import { join } from "node:path";
+import { openDb } from "../src/db";
+import { loadOrCreateKey } from "../src/lib/crypto";
+import { extractFromText } from "../src/lib/extract";
+
+const FIXTURE_TEXT = `
+Sample Diagnostics — Final Report
+Collected: 15 Jan 2026
+CHEMISTRY
+Glucose (Fasting)   100  mg/dL   (70-99)  H
+LIPIDS
+LDL Cholesterol     3.1  mmol/L  (<3.4)
+`;
+
+describe("extractFromText", () => {
+  test("passes text to LLM and validates the draft shape", async () => {
+    let userPrompt = "";
+    const mock = (async (_: any, init: any) => {
+      userPrompt = JSON.parse(String(init.body)).messages[1].content;
+      return new Response(JSON.stringify({ choices: [{ message: { content: JSON.stringify({
+        collectedDate: "2026-01-15",
+        labName: "Sample Diagnostics",
+        markers: [
+          { panel: "chemistry", name: "Glucose (Fasting)", value: "100", unit: "mg/dL", referenceRange: "70-99", flagged: true },
+          { panel: "lipids", name: "LDL Cholesterol", value: "3.1", unit: "mmol/L", referenceRange: "<3.4", flagged: false },
+        ],
+      }) } }] }), { status: 200 });
+    }) as typeof fetch;
+
+    const dir = mkdtempSync(join(tmpdir(), "helios-"));
+    const draft = await extractFromText({ db: openDb(dir), key: loadOrCreateKey(dir), fetchImpl: mock }, FIXTURE_TEXT);
+    expect(userPrompt).toContain("Glucose (Fasting)");
+    expect(draft.markers).toHaveLength(2);
+    expect(draft.collectedDate).toBe("2026-01-15");
+    expect(draft.markers[0].flagged).toBe(true);
+  });
+
+  test("malformed LLM output → llm_error, not a crash", async () => {
+    const mock = (async () => new Response(JSON.stringify({ choices: [{ message: { content: '{"markers": "not an array"}' } }] }), { status: 200 })) as unknown as typeof fetch;
+    const dir = mkdtempSync(join(tmpdir(), "helios-"));
+    expect(extractFromText({ db: openDb(dir), key: loadOrCreateKey(dir), fetchImpl: mock }, "x")).rejects.toThrow(/llm_error/);
+  });
+});

server/test/labs-upload.test.ts

@@ -0,0 +1,70 @@
+import { describe, expect, test } from "bun:test";
+import { mkdtempSync } from "node:fs";
+import { tmpdir } from "node:os";
+import { join } from "node:path";
+import { createApp } from "../src/app";
+import { openDb } from "../src/db";
+import { loadOrCreateKey } from "../src/lib/crypto";
+
+// Minimal one-page PDF with a text object — enough for unpdf to open and read.
+const TINY_PDF = `%PDF-1.4
+1 0 obj<</Type/Catalog/Pages 2 0 R>>endobj
+2 0 obj<</Type/Pages/Kids[3 0 R]/Count 1>>endobj
+3 0 obj<</Type/Page/Parent 2 0 R/MediaBox[0 0 612 792]/Contents 4 0 R/Resources<</Font<</F1 5 0 R>>>>>>endobj
+4 0 obj<</Length 60>>stream
+BT /F1 12 Tf 72 720 Td (Glucose 100 mg/dL 70-99 H) Tj ET
+endstream
+endobj
+5 0 obj<</Type/Font/Subtype/Type1/BaseFont/Helvetica>>endobj
+trailer<</Root 1 0 R>>`;
+
+async function authedApp(fetchImpl: typeof fetch) {
+  const dir = mkdtempSync(join(tmpdir(), "helios-"));
+  const app = createApp({ db: openDb(dir), key: loadOrCreateKey(dir), dataDir: dir, llmFetch: fetchImpl });
+  const j = (b: unknown) => ({ method: "POST", headers: { "content-type": "application/json" }, body: JSON.stringify(b) });
+  await app.request("/api/setup", j({ password: "hunter2hunter2" }));
+  const cookie = (await app.request("/api/login", j({ password: "hunter2hunter2" }))).headers.get("set-cookie")!;
+  return { app, cookie };
+}
+
+const llmOk = (async () => new Response(JSON.stringify({ choices: [{ message: { content: JSON.stringify({
+  collectedDate: "2026-01-15", labName: "Sample Diagnostics",
+  markers: [{ panel: null, name: "Glucose", value: "100", unit: "mg/dL", referenceRange: "70-99", flagged: true }],
+}) } }] }), { status: 200 })) as unknown as typeof fetch;
+
+describe("labs upload", () => {
+  test("PDF upload → pending draft with extracted markers", async () => {
+    const { app, cookie } = await authedApp(llmOk);
+    const fd = new FormData();
+    fd.append("file", new File([TINY_PDF], "results.pdf", { type: "application/pdf" }));
+    const up = await app.request("/api/labs/upload", { method: "POST", headers: { cookie }, body: fd });
+    expect(up.status).toBe(201);
+    const { id } = await up.json();
+
+    const list = await (await app.request("/api/labs/drafts", { headers: { cookie } })).json();
+    expect(list.drafts).toHaveLength(1);
+    expect(list.drafts[0].id).toBe(id);
+    expect(list.drafts[0].status).toBe("pending");
+    expect(list.drafts[0].markerCount).toBe(1);
+  });
+
+  test("non-PDF rejected", async () => {
+    const { app, cookie } = await authedApp(llmOk);
+    const fd = new FormData();
+    fd.append("file", new File(["hi"], "notes.txt", { type: "text/plain" }));
+    const up = await app.request("/api/labs/upload", { method: "POST", headers: { cookie }, body: fd });
+    expect(up.status).toBe(400);
+  });
+
+  test("LLM failure → draft stored with error, not a 500", async () => {
+    const llmDown = (async () => new Response("x", { status: 500 })) as unknown as typeof fetch;
+    const { app, cookie } = await authedApp(llmDown);
+    const fd = new FormData();
+    fd.append("file", new File([TINY_PDF], "r.pdf", { type: "application/pdf" }));
+    const up = await app.request("/api/labs/upload", { method: "POST", headers: { cookie }, body: fd });
+    expect(up.status).toBe(201);
+    const list = await (await app.request("/api/labs/drafts", { headers: { cookie } })).json();
+    expect(list.drafts[0].error).toMatch(/llm_error/);
+    expect(list.drafts[0].markerCount).toBe(0);
+  });
+});

server/test/settings.test.ts

@@ -11,7 +11,7 @@ import { loadOrCreateKey } from "../src/lib/crypto";
 async function authedApp() {
   const dir = mkdtempSync(join(tmpdir(), "helios-"));
   const db = openDb(dir);
-  const app = createApp({ db, key: loadOrCreateKey(dir) });
+  const app = createApp({ db, key: loadOrCreateKey(dir), dataDir: dir });
   const j = (b: unknown) => ({ method: "POST", headers: { "content-type": "application/json" }, body: JSON.stringify(b) });
   await app.request("/api/setup", j({ password: "hunter2hunter2" }));
   const cookie = (await app.request("/api/login", j({ password: "hunter2hunter2" }))).headers.get("set-cookie")!;

shared/src/types.ts

@@ -20,3 +20,20 @@ export const SettingsUpdate = z.object({
   llmKey: z.string().min(1).optional(),
 });
 export type SettingsUpdate = z.infer<typeof SettingsUpdate>;
+
+export const ExtractedMarker = z.object({
+  panel: z.string().nullable().default(null),
+  name: z.string().min(1),
+  value: z.string().min(1),
+  unit: z.string().nullable().default(null),
+  referenceRange: z.string().nullable().default(null),
+  flagged: z.boolean().default(false),
+});
+export type ExtractedMarker = z.infer<typeof ExtractedMarker>;
+
+export const ExtractedDraft = z.object({
+  collectedDate: z.string().nullable().default(null),
+  labName: z.string().nullable().default(null),
+  markers: z.array(ExtractedMarker).default([]),
+});
+export type ExtractedDraft = z.infer<typeof ExtractedDraft>;