fix(api): add /api/readyz to authMiddleware bypass list (GRO-2687)

/api/readyz was returning 401 Unauthorized in UAT (GRO-2692 Shedward
regression). The authMiddleware for /api/* did not whitelist /api/readyz,
causing every unauthenticated probe request to be rejected.

Add /api/readyz to the bypass condition alongside /api/auth/* and
/api/health. Add readyz-auth-bypass.test.ts confirming the route passes
through the middleware without auth and that non-whitelisted paths still
block (503 when auth not configured).

Closes GRO-2692 regression (UAT fail).

UAT_PLAYBOOK.md

@@ -65,8 +65,11 @@ Expected: one row, `role = 'groomer'`. If zero rows return, the request hit the
 | # | Scenario | Steps | Expected |
 |---|----------|-------|----------|
 | TC-API-0.1 | Unauthenticated health check | GET /api/health | 200 OK, `{"status":"ok"}` |
+| TC-API-0.2 | DB-touching readiness check — healthy (GRO-2678) | GET /api/readyz | 200 OK, `{"status":"ready"}` |
+| TC-API-0.3 | DB-touching readiness check — response body safe | GET /api/readyz and inspect body | Body contains only `status` and (on error) `check` fields — no raw SQL, driver messages, or stack traces |
 
 > **Note (GRO-1544):** Health endpoint registered on `api` basePath before auth middleware at `/api/health`. The old path `/health` was incorrect (routed to web pod via HTTPRoute `/*` rule).
+> **Note (GRO-2678):** `/api/readyz` is a separate DB-touching endpoint for monitoring. It is intentionally NOT used for K8s liveness/readiness probes — those remain DB-less to avoid pod cycling on transient DB blips.
 
 ### 4.1 Authentication
 

apps/api/src/__tests__/auth.test.ts

@@ -69,9 +69,14 @@ describe("auth init", () => {
   beforeEach(() => {
     dbSelectResult = [];
     vi.clearAllMocks();
+    // Stub fetch so OIDC discovery requests resolve instantly during tests.
+    // Without this, AbortSignal.timeout(5000) in auth.ts races with vitest's
+    // 5000ms default test timeout and causes flaky failures.
+    vi.stubGlobal("fetch", vi.fn().mockResolvedValue({ ok: false, status: 503 }));
   });
 
   afterEach(() => {
+    vi.unstubAllGlobals();
     process.env = { ...originalEnv };
   });
 

packages/db/src/reset.ts

@@ -32,7 +32,7 @@
  */
 import postgres from "postgres";
 import { drizzle } from "drizzle-orm/postgres-js";
-import { migrate } from "drizzle-orm/postgres-js/migrator";
+import { execSync } from "node:child_process";
 import { fileURLToPath } from "node:url";
 import { dirname, resolve } from "node:path";
 import * as schema from "./schema.js";
@@ -46,7 +46,6 @@ import {
 
 const __filename = fileURLToPath(import.meta.url);
 const __dirname = dirname(__filename);
-const MIGRATIONS_FOLDER = resolve(__dirname, "../migrations");
 
 async function reset() {
   const url = process.env.DATABASE_URL;
@@ -73,7 +72,7 @@ async function reset() {
   // across processes regardless of how many connections the work uses —
   // it does NOT require the work to share the lock's session.
   //
-  // Therefore `max` must be ≥ 2: 1 reserved for the lock + ≥1 free for
+  // Therefore `max` must be >= 2: 1 reserved for the lock + >=1 free for
   // the work. `max: 1` would let `reserve()` consume the only connection
   // and every query inside the callback would block forever waiting for
   // a connection that never frees (connection-starvation deadlock). We
@@ -122,7 +121,15 @@ async function reset() {
       console.log("✓ All tables and enums dropped\n");
 
       console.log("Running migrations...");
-      await migrate(db, { migrationsFolder: MIGRATIONS_FOLDER });
+      // GRO-2672: drizzle-orm's migrate() has a high-water-mark bug that skips
+      // migrations with stale `when` timestamps (0001, 0003, 0010, 0011). Use
+      // drizzle-kit instead -- it applies migrations by hash, matching the K8s
+      // migrate Job behaviour exactly.
+      execSync("pnpm exec drizzle-kit migrate", {
+        stdio: "inherit",
+        env: { ...process.env },
+        cwd: resolve(__dirname, ".."),
+      });
       console.log("✓ Migrations applied\n");
 
       console.log("Seeding database...");

src/__tests__/auth.test.ts

@@ -69,9 +69,14 @@ describe("auth init", () => {
   beforeEach(() => {
     dbSelectResult = [];
     vi.clearAllMocks();
+    // Stub fetch so OIDC discovery requests resolve instantly during tests.
+    // Without this, AbortSignal.timeout(5000) in auth.ts races with vitest's
+    // 5000ms default test timeout and causes flaky failures.
+    vi.stubGlobal("fetch", vi.fn().mockResolvedValue({ ok: false, status: 503 }));
   });
 
   afterEach(() => {
+    vi.unstubAllGlobals();
     process.env = { ...originalEnv };
   });
 

src/__tests__/readyz-auth-bypass.test.ts

@@ -0,0 +1,44 @@
+import { describe, it, expect, vi } from "vitest";
+import { Hono } from "hono";
+
+// Mock auth lib so getAuth() throws — non-bypass paths hit the 503 "not configured" guard.
+vi.mock("../lib/auth.js", () => ({
+  getAuth: () => {
+    throw new Error("auth not configured");
+  },
+  initAuth: vi.fn(),
+  getActiveProviders: vi.fn(() => []),
+}));
+
+describe("authMiddleware bypass: /api/readyz", () => {
+  it("serves /api/readyz without auth (bypass before auth check)", async () => {
+    // Ensure AUTH_DISABLED is not set so the bypass is exercised, not AUTH_DISABLED shortcut.
+    const prev = process.env.AUTH_DISABLED;
+    delete process.env.AUTH_DISABLED;
+
+    const { authMiddleware } = await import("../middleware/auth.js");
+    const app = new Hono();
+    app.use("/api/*", authMiddleware);
+    app.get("/api/readyz", (c) => c.json({ status: "ok" }, 200));
+
+    const res = await app.request("/api/readyz", { method: "GET" });
+    expect(res.status).toBe(200);
+
+    if (prev !== undefined) process.env.AUTH_DISABLED = prev;
+  });
+
+  it("blocks non-whitelisted /api/* paths when auth is not configured", async () => {
+    const prev = process.env.AUTH_DISABLED;
+    delete process.env.AUTH_DISABLED;
+
+    const { authMiddleware } = await import("../middleware/auth.js");
+    const app = new Hono();
+    app.use("/api/*", authMiddleware);
+    app.get("/api/staff", (c) => c.json({ ok: true }, 200));
+
+    const res = await app.request("/api/staff", { method: "GET" });
+    expect(res.status).toBe(503);
+
+    if (prev !== undefined) process.env.AUTH_DISABLED = prev;
+  });
+});

src/__tests__/readyz.test.ts

@@ -0,0 +1,87 @@
+import { describe, it, expect, vi, beforeEach } from "vitest";
+import { Hono } from "hono";
+
+// ─── Mock db module ───────────────────────────────────────────────────────────
+
+let selectImpl: () => Promise<unknown>;
+
+vi.mock("@groombook/db", () => {
+  const staff = new Proxy(
+    { _name: "staff" },
+    {
+      get(_target, prop) {
+        if (prop === "_name") return "staff";
+        return { table: "staff", column: prop };
+      },
+    }
+  );
+
+  return {
+    getDb: () => ({
+      select: (_fields: unknown) => ({
+        from: (_table: unknown) => ({
+          limit: (_n: number) => selectImpl(),
+        }),
+      }),
+    }),
+    staff,
+  };
+});
+
+// ─── Build test app ───────────────────────────────────────────────────────────
+
+async function makeApp() {
+  // Import after mocks are in place
+  const { getDb, staff } = await import("@groombook/db");
+
+  const app = new Hono();
+  app.get("/api/readyz", async (c) => {
+    try {
+      await getDb().select({ id: staff.id }).from(staff).limit(1);
+      return c.json({ status: "ready" }, 200);
+    } catch (err) {
+      console.error("[readyz] DB check failed:", err);
+      return c.json({ status: "degraded", check: "db" }, 503);
+    }
+  });
+  return app;
+}
+
+// ─── Tests ────────────────────────────────────────────────────────────────────
+
+describe("GET /api/readyz", () => {
+  beforeEach(() => {
+    vi.restoreAllMocks();
+  });
+
+  it("returns 200 {status:'ready'} when DB query succeeds", async () => {
+    selectImpl = () => Promise.resolve([{ id: "staff-1" }]);
+
+    const app = await makeApp();
+    const res = await app.request("/api/readyz", { method: "GET" });
+    const body = (await res.json()) as Record<string, unknown>;
+
+    expect(res.status).toBe(200);
+    expect(body.status).toBe("ready");
+  });
+
+  it("returns 503 {status:'degraded',check:'db'} when DB query throws", async () => {
+    selectImpl = () => Promise.reject(new Error("42P01: relation staff does not exist"));
+
+    const consoleSpy = vi.spyOn(console, "error").mockImplementation(() => {});
+
+    const app = await makeApp();
+    const res = await app.request("/api/readyz", { method: "GET" });
+    const body = (await res.json()) as Record<string, unknown>;
+
+    expect(res.status).toBe(503);
+    expect(body.status).toBe("degraded");
+    expect(body.check).toBe("db");
+
+    // Raw SQL / driver error must NOT appear in the response body
+    expect(JSON.stringify(body)).not.toContain("42P01");
+    expect(JSON.stringify(body)).not.toContain("relation");
+
+    consoleSpy.mockRestore();
+  });
+});

src/index.ts

@@ -65,6 +65,17 @@ app.use(
 app.get("/health", (c) => c.json({ status: "ok" }));
 // /api/health: used by Gateway HTTPRoute (/api/* → API pod)
 app.get("/api/health", (c) => c.json({ status: "ok" }));
+// /api/readyz: DB-touching deep health check consumed by monitoring (not K8s probes)
+// Distinct from /health so a dropped schema triggers an alert without cycling pods (GRO-2678)
+app.get("/api/readyz", async (c) => {
+  try {
+    await getDb().select({ id: staff.id }).from(staff).limit(1);
+    return c.json({ status: "ready" }, 200);
+  } catch (err) {
+    console.error("[readyz] DB check failed:", err);
+    return c.json({ status: "degraded", check: "db" }, 503);
+  }
+});
 
 // Public booking routes — no auth required, must be registered before auth middleware
 app.route("/api/book", bookRouter);

src/lib/auth.ts

@@ -329,5 +329,10 @@ export async function initAuth(): Promise<void> {
     });
   })();
 
-  await authInitPromise;
+  try {
+    await authInitPromise;
+  } catch (err) {
+    authInitPromise = null; // allow retry on next call
+    throw err;
+  }
 }

src/middleware/auth.ts

@@ -23,7 +23,7 @@ if (process.env.AUTH_DISABLED === "true") {
 }
 
 export const authMiddleware: MiddlewareHandler = async (c, next) => {
-  if (c.req.path.startsWith("/api/auth/") || c.req.path === "/api/health") {
+  if (c.req.path.startsWith("/api/auth/") || c.req.path === "/api/health" || c.req.path === "/api/readyz") {
     await next();
     return;
   }