apps/web/auth.ts

@@ -1,7 +1,6 @@
 import NextAuth from "next-auth";
 import { env } from "@/lib/env";
-import { db } from "@/lib/db/client";
-import { users } from "@/lib/db/schema";
+import { oidClaim, resolveUserId } from "@/lib/auth/identity";
 import { syncUserGroupsFromClaim } from "@/lib/auth/sync-groups";
 
 /**
@@ -41,27 +40,18 @@ export const { auth, handlers, signIn, signOut } = NextAuth({
         const iss = (profile.iss as string | undefined) ?? env().OIDC_ISSUER;
         if (!sub) throw new Error("OIDC profile missing `sub` claim");
 
-        const row = await db
-          .insert(users)
-          .values({
-            oidcSub: sub,
-            oidcIss: iss,
-            email: profile.email ?? null,
-            name: profile.name ?? null,
-            picture: (profile.picture as string | undefined) ?? null,
-          })
-          .onConflictDoUpdate({
-            target: [users.oidcIss, users.oidcSub],
-            set: {
-              email: profile.email ?? null,
-              name: profile.name ?? null,
-              picture: (profile.picture as string | undefined) ?? null,
-              lastSeenAt: new Date(),
-            },
-          })
-          .returning({ id: users.id });
+        // Shared with the MCP path (lib/mcp/context.ts). On EntraID the `oid`
+        // claim is what keeps the two surfaces resolving to one account —
+        // `sub` differs per app registration there. See lib/auth/identity.ts.
+        const userId = await resolveUserId({
+          iss,
+          sub,
+          oid: oidClaim(profile),
+          email: profile.email ?? null,
+          name: profile.name ?? null,
+          picture: (profile.picture as string | undefined) ?? null,
+        });
 
-        const userId = row[0]?.id;
         token.userId = userId;
         token.sub = sub;
         token.iss = iss;
@@ -71,10 +61,15 @@ export const { auth, handlers, signIn, signOut } = NextAuth({
         // wipes the user's existing memberships, which is the conservative
         // choice (don't keep stale grants alive if the IdP stopped
         // asserting them).
+        //
+        // The whole profile goes in, not just `profile.groups`: an absent
+        // claim means one thing on its own and something else entirely next
+        // to EntraID's overage markers, and only the second case must abort.
+        // A GroupsOverageError thrown here fails the sign-in, which is the
+        // intent — it leaves the user's existing memberships untouched
+        // instead of silently deleting them.
         if (userId) {
-          // `profile.groups` is untyped at the next-auth boundary — coerce.
-          const claimGroups = (profile as { groups?: unknown }).groups;
-          await syncUserGroupsFromClaim(userId, iss, claimGroups);
+          await syncUserGroupsFromClaim(userId, iss, profile);
         }
       }
       return token;

apps/web/drizzle/0005_user_oid.sql

@@ -0,0 +1,29 @@
+-- EntraID identity: key users on `oid` when the IdP emits it.
+--
+-- EntraID's `sub` is a PAIRWISE identifier — derived from the token recipient,
+-- so the Web UI app registration and the MCP app registration hand out
+-- different `sub` values for the same person. Both `auth.ts` and
+-- `lib/mcp/context.ts` upsert on (oidc_iss, oidc_sub), so on EntraID one human
+-- resolves to two rows: they sign into the Web UI, connect an MCP client, and
+-- land in an empty account with their memories nowhere to be seen. Nothing
+-- errors, which is what makes it dangerous.
+--
+-- `oid` is the user's directory object id, which Microsoft documents as
+-- constant for a user across every application in a tenant. Recording it gives
+-- us a key that holds across both surfaces.
+--
+-- Nullable on purpose: Authentik, Keycloak and Okta emit no `oid`, and there
+-- `sub` is already application-independent. Those deployments keep using
+-- (oidc_iss, oidc_sub) and are untouched by this migration.
+
+ALTER TABLE "users" ADD COLUMN "oidc_oid" text;
+
+-- Partial index. Every non-EntraID row holds NULL here; a plain unique index
+-- would treat those as colliding and permit exactly one such user.
+CREATE UNIQUE INDEX "users_iss_oid_uq"
+  ON "users" ("oidc_iss", "oidc_oid")
+  WHERE "oidc_oid" IS NOT NULL;
+
+-- No backfill. `oid` is only knowable from a token, so existing rows adopt
+-- theirs on the owner's next sign-in (see `adoptLegacyRow` in
+-- lib/auth/identity.ts). Backfilling would mean guessing.

apps/web/lib/auth/identity.test.ts

@@ -0,0 +1,165 @@
+import { afterAll, beforeEach, describe, expect, test } from "vitest";
+
+/**
+ * Identity resolution across the two surfaces.
+ *
+ * The bug these guard against is silent: on EntraID the Web UI and the MCP
+ * endpoint see different `sub` values for the same person, both code paths
+ * UPSERT rather than fail, and the result is two accounts — the user signs in,
+ * connects an MCP client, and finds their memories gone. Nothing errors, so
+ * only a test that asserts "same person ⇒ same row id" catches it.
+ */
+const { db, pg } = await import("@/lib/db/client");
+const { users } = await import("@/lib/db/schema");
+const { resolveUserId, oidClaim } = await import("@/lib/auth/identity");
+const { eq } = await import("drizzle-orm");
+
+/** `noUncheckedIndexedAccess` is on; narrow once rather than at every use. */
+function first<T>(rows: T[]): T {
+  const row = rows[0];
+  if (!row) throw new Error("expected at least one row");
+  return row;
+}
+
+const ISS = "https://login.microsoftonline.com/test-tenant/v2.0";
+
+/** Distinct `sub` values, as EntraID's pairwise identifiers would be. */
+const WEB_SUB = "pairwise-sub-for-web-registration";
+const MCP_SUB = "pairwise-sub-for-mcp-registration";
+const OID = "00000000-1111-2222-3333-444444444444";
+
+function claims(overrides: Record<string, unknown> = {}) {
+  return {
+    iss: ISS,
+    sub: WEB_SUB,
+    oid: OID,
+    email: "person@example.com",
+    name: "Person",
+    picture: null,
+    ...overrides,
+  } as Parameters<typeof resolveUserId>[0];
+}
+
+beforeEach(async () => {
+  await db.delete(users).where(eq(users.oidcIss, ISS));
+});
+
+afterAll(async () => {
+  await db.delete(users).where(eq(users.oidcIss, ISS));
+  await pg.end();
+});
+
+describe("oidClaim", () => {
+  test("reads a string oid", () => {
+    expect(oidClaim({ oid: OID })).toBe(OID);
+  });
+
+  test("is null when absent, blank, or not a string", () => {
+    expect(oidClaim({})).toBeNull();
+    expect(oidClaim({ oid: "   " })).toBeNull();
+    expect(oidClaim({ oid: 42 })).toBeNull();
+    expect(oidClaim(null)).toBeNull();
+  });
+});
+
+describe("resolveUserId with an oid (EntraID)", () => {
+  test("both surfaces resolve to ONE row despite different subs", async () => {
+    const fromWeb = await resolveUserId(claims({ sub: WEB_SUB }));
+    const fromMcp = await resolveUserId(claims({ sub: MCP_SUB }));
+
+    expect(fromMcp).toBe(fromWeb);
+
+    const rows = await db.select().from(users).where(eq(users.oidcIss, ISS));
+    expect(rows).toHaveLength(1);
+  });
+
+  test("does not rewrite oidc_sub once the row exists", async () => {
+    await resolveUserId(claims({ sub: WEB_SUB }));
+    await resolveUserId(claims({ sub: MCP_SUB }));
+
+    const rows = await db.select().from(users).where(eq(users.oidcIss, ISS));
+    // Whichever arrived first stays put; flip-flopping it on every request
+    // could collide with the (iss, sub) unique index.
+    expect(first(rows).oidcSub).toBe(WEB_SUB);
+    expect(first(rows).oidcOid).toBe(OID);
+  });
+
+  test("adopts a pre-migration row instead of stranding it", async () => {
+    // A deployment that signed this person in before 0005 ran: correct sub,
+    // no oid recorded.
+    const legacy = first(
+      await db
+        .insert(users)
+        .values({ oidcIss: ISS, oidcSub: WEB_SUB, email: "old@example.com" })
+        .returning({ id: users.id }),
+    );
+
+    const resolved = await resolveUserId(claims({ sub: WEB_SUB }));
+
+    expect(resolved).toBe(legacy.id);
+    const rows = await db.select().from(users).where(eq(users.oidcIss, ISS));
+    expect(rows).toHaveLength(1);
+    expect(first(rows).oidcOid).toBe(OID);
+  });
+
+  test("refreshes profile fields on an existing row", async () => {
+    await resolveUserId(claims({ name: "Old Name" }));
+    await resolveUserId(claims({ sub: MCP_SUB, name: "New Name" }));
+
+    const rows = await db.select().from(users).where(eq(users.oidcIss, ISS));
+    expect(first(rows).name).toBe("New Name");
+  });
+
+  test("concurrent first-contact from both surfaces yields one row", async () => {
+    const [a, b] = await Promise.all([
+      resolveUserId(claims({ sub: WEB_SUB })),
+      resolveUserId(claims({ sub: MCP_SUB })),
+    ]);
+
+    expect(a).toBe(b);
+    const rows = await db.select().from(users).where(eq(users.oidcIss, ISS));
+    expect(rows).toHaveLength(1);
+  });
+
+  test("different people in one tenant stay separate", async () => {
+    const one = await resolveUserId(claims());
+    const two = await resolveUserId(
+      claims({ sub: "other-sub", oid: "99999999-1111-2222-3333-444444444444" }),
+    );
+
+    expect(two).not.toBe(one);
+    const rows = await db.select().from(users).where(eq(users.oidcIss, ISS));
+    expect(rows).toHaveLength(2);
+  });
+});
+
+describe("resolveUserId without an oid (Authentik and friends)", () => {
+  test("keys on (iss, sub) exactly as before", async () => {
+    const initial = await resolveUserId(claims({ oid: null }));
+    const again = await resolveUserId(claims({ oid: null, name: "Renamed" }));
+
+    expect(again).toBe(initial);
+    const rows = await db.select().from(users).where(eq(users.oidcIss, ISS));
+    expect(rows).toHaveLength(1);
+    expect(first(rows).oidcOid).toBeNull();
+    expect(first(rows).name).toBe("Renamed");
+  });
+
+  test("distinct subs are distinct people", async () => {
+    await resolveUserId(claims({ oid: null, sub: "a" }));
+    await resolveUserId(claims({ oid: null, sub: "b" }));
+
+    const rows = await db.select().from(users).where(eq(users.oidcIss, ISS));
+    expect(rows).toHaveLength(2);
+  });
+
+  test("several oid-less users coexist — the unique index is partial", async () => {
+    // A non-partial unique index on (iss, oid) would allow exactly one NULL
+    // pair and reject everyone after the first.
+    for (const sub of ["u1", "u2", "u3"]) {
+      await resolveUserId(claims({ oid: null, sub }));
+    }
+    const rows = await db.select().from(users).where(eq(users.oidcIss, ISS));
+    expect(rows).toHaveLength(3);
+  });
+});

apps/web/lib/auth/identity.ts

@@ -0,0 +1,125 @@
+import { and, eq, isNull } from "drizzle-orm";
+import { db } from "@/lib/db/client";
+import { users } from "@/lib/db/schema";
+
+/**
+ * Resolving OIDC claims to the internal `users.id`.
+ *
+ * Both surfaces come through here — the Web UI (`auth.ts`) and the MCP
+ * endpoint (`lib/mcp/context.ts`) — and that is the point. They each used to
+ * carry their own copy of this upsert, which is how the two drifted into
+ * disagreeing about who a user is.
+ *
+ * ## Why `oid` exists here
+ *
+ * Authentik's `sub` is `user.uid`, identical across every provider, so
+ * (iss, sub) identifies a person. EntraID's `sub` is PAIRWISE: Microsoft
+ * derives it from the token recipient, so the Web UI app registration and the
+ * MCP app registration emit different `sub` values for the same human. Keyed
+ * on `sub`, that person gets two rows — they sign into the Web UI, connect
+ * Claude Code, and find an empty account. Both paths upsert, so nothing
+ * errors; the split is completely silent.
+ *
+ * `oid` is the directory object id, which Microsoft documents as constant for
+ * a user across every application in a tenant. When it's present it wins.
+ * When it's absent (Authentik, Keycloak, Okta) behaviour is exactly as before.
+ */
+
+/** Extract a usable EntraID `oid` claim, or null on IdPs that don't emit one. */
+export function oidClaim(claims: unknown): string | null {
+  const raw = (claims as { oid?: unknown } | null | undefined)?.oid;
+  if (typeof raw !== "string") return null;
+  const trimmed = raw.trim();
+  return trimmed.length > 0 ? trimmed : null;
+}
+
+export interface IdentityInput {
+  iss: string;
+  sub: string;
+  /** EntraID object id, or null. */
+  oid: string | null;
+  email: string | null;
+  name: string | null;
+  picture: string | null;
+}
+
+/** Postgres unique-violation. */
+function isUniqueViolation(err: unknown): boolean {
+  return (err as { code?: unknown } | null)?.code === "23505";
+}
+
+/**
+ * Resolve (creating if needed) the `users` row for a set of verified claims.
+ *
+ * Resolution order when `oid` is present:
+ *
+ *   1. a row already keyed on this `oid` — the steady state
+ *   2. a pre-`oid` row for the same (iss, sub), which gets its `oid`
+ *      backfilled in place. This is how a deployment that ran before the
+ *      0005 migration keeps its accounts instead of stranding them.
+ *   3. insert
+ *
+ * Without `oid` this collapses to the original (iss, sub) upsert.
+ */
+export async function resolveUserId(input: IdentityInput): Promise<string> {
+  const { iss, sub, oid, email, name, picture } = input;
+  const profile = { email, name, picture, lastSeenAt: new Date() };
+
+  if (oid) {
+    // 1. Steady state.
+    //
+    // Deliberately does NOT touch `oidc_sub`. The stored value is whichever
+    // app registration this person first arrived through; rewriting it on
+    // every request would flip it back and forth between the Web and MCP
+    // values and could collide with the (iss, sub) unique index.
+    const byOid = await db
+      .update(users)
+      .set(profile)
+      .where(and(eq(users.oidcIss, iss), eq(users.oidcOid, oid)))
+      .returning({ id: users.id });
+    if (byOid[0]) return byOid[0].id;
+
+    // 2. Adopt a row created before `oid` was recorded.
+    const adopted = await db
+      .update(users)
+      .set({ ...profile, oidcOid: oid })
+      .where(
+        and(eq(users.oidcIss, iss), eq(users.oidcSub, sub), isNull(users.oidcOid)),
+      )
+      .returning({ id: users.id });
+    if (adopted[0]) return adopted[0].id;
+  }
+
+  // 3. Insert. The conflict target stays (iss, sub) because that is the index
+  //    every row has; a concurrent writer racing us on `oid` instead is caught
+  //    below.
+  try {
+    const inserted = await db
+      .insert(users)
+      .values({ oidcIss: iss, oidcSub: sub, oidcOid: oid, email, name, picture })
+      .onConflictDoUpdate({
+        target: [users.oidcIss, users.oidcSub],
+        set: profile,
+      })
+      .returning({ id: users.id });
+    if (inserted[0]) return inserted[0].id;
+  } catch (err) {
+    // Two requests for the same person arriving together through DIFFERENT
+    // app registrations: same `oid`, different `sub`, so the (iss, sub)
+    // conflict target doesn't fire and the partial (iss, oid) index rejects
+    // the loser. Fall through and read the winner's row.
+    if (!isUniqueViolation(err)) throw err;
+  }
+
+  const existing = await db
+    .select({ id: users.id })
+    .from(users)
+    .where(
+      oid
+        ? and(eq(users.oidcIss, iss), eq(users.oidcOid, oid))
+        : and(eq(users.oidcIss, iss), eq(users.oidcSub, sub)),
+    )
+    .limit(1);
+  if (!existing[0]) throw new Error("user upsert failed and not found on re-read");
+  return existing[0].id;
+}

apps/web/lib/auth/jwt.test.ts

@@ -0,0 +1,226 @@
+import { createServer, type Server } from "node:http";
+import { AddressInfo } from "node:net";
+import { SignJWT, exportJWK, generateKeyPair } from "jose";
+import type { JWK, KeyLike } from "jose";
+import { afterEach, beforeEach, describe, expect, test, vi } from "vitest";
+
+/**
+ * The JWKS location is discovered, not assumed.
+ *
+ * `${issuer}/jwks/` used to be hardcoded here. That is an Authentik
+ * convention — EntraID serves its keys at
+ * `https://login.microsoftonline.com/{tenant}/discovery/v2.0/keys`, so on
+ * EntraID the hardcoded path 404s and NO MCP token can ever verify. These
+ * tests pin the three behaviours that make the discovery path safe to ship:
+ * discovery is honoured, failure degrades to the old path rather than to a
+ * broken deployment, and it happens once rather than per request.
+ *
+ * A real loopback HTTP server is used rather than a `fetch` mock because jose
+ * fetches the key set through `node:http` directly, not through global
+ * `fetch` — a mocked `fetch` would silently never be consulted for the JWKS
+ * request, and the assertion about *which* URL was used would prove nothing.
+ */
+
+const TENANT = "11111111-2222-3333-4444-555555555555";
+const AUDIENCE = "99999999-8888-7777-6666-555555555555";
+
+/** Paths the fake IdP was asked for, in order. */
+let requested: string[] = [];
+/** Response the fake IdP gives for the discovery document. */
+let discoveryResponse: { status: number; body: string };
+let server: Server;
+let origin: string;
+let privateKey: KeyLike;
+let publicJwk: JWK;
+
+/** Authentik-shaped issuer: application-scoped path, trailing slash. */
+function authentikIssuer(): string {
+  return `${origin}/application/o/shared-memory-mcp/`;
+}
+
+/** EntraID-shaped issuer: tenant-scoped, no trailing slash. */
+function entraIssuer(): string {
+  return `${origin}/${TENANT}/v2.0`;
+}
+
+/** Where an EntraID discovery document points for keys. */
+function entraKeysPath(): string {
+  return `/${TENANT}/discovery/v2.0/keys`;
+}
+
+beforeEach(async () => {
+  const pair = await generateKeyPair("RS256");
+  privateKey = pair.privateKey;
+  publicJwk = { ...(await exportJWK(pair.publicKey)), kid: "test-key", alg: "RS256", use: "sig" };
+  requested = [];
+
+  server = createServer((req, res) => {
+    requested.push(req.url ?? "");
+    if (req.url?.endsWith("/.well-known/openid-configuration")) {
+      res.writeHead(discoveryResponse.status, { "content-type": "application/json" });
+      res.end(discoveryResponse.body);
+      return;
+    }
+    // Every other path is treated as a key set endpoint. Which path the
+    // request actually arrived on is the thing under test.
+    res.writeHead(200, { "content-type": "application/json" });
+    res.end(JSON.stringify({ keys: [publicJwk] }));
+  });
+
+  await new Promise<void>((resolve) => server.listen(0, "127.0.0.1", resolve));
+  origin = `http://127.0.0.1:${(server.address() as AddressInfo).port}`;
+});
+
+afterEach(async () => {
+  // The key set is memoised on globalThis, which survives vi.resetModules().
+  // Without clearing it, the second test in this file would silently reuse
+  // the first test's resolution and assert nothing.
+  delete (globalThis as Record<string, unknown>).__sharedMemoryJwks;
+  delete (globalThis as Record<string, unknown>).__sharedMemoryJwksRetryAt;
+  delete process.env.OIDC_ISSUER_MCP;
+  delete process.env.OIDC_AUDIENCE;
+  await new Promise<void>((resolve) => server.close(() => resolve()));
+});
+
+/**
+ * Import `authenticateBearer` fresh so it observes the env vars this test set
+ * (lib/env.ts caches its parse in a module singleton).
+ */
+async function loadAuthenticateBearer() {
+  vi.resetModules();
+  const mod = await import("@/lib/auth/jwt");
+  return mod.authenticateBearer;
+}
+
+async function signAccessToken(issuer: string): Promise<string> {
+  return new SignJWT({ groups: ["memory-users"] })
+    .setProtectedHeader({ alg: "RS256", kid: "test-key" })
+    .setIssuer(issuer)
+    .setAudience(AUDIENCE)
+    .setSubject("user-object-id")
+    .setIssuedAt()
+    .setExpirationTime("5m")
+    .sign(privateKey);
+}
+
+function discoveryPathsSeen(): string[] {
+  return requested.filter((p) => p.endsWith("/.well-known/openid-configuration"));
+}
+
+describe("MCP JWKS resolution", () => {
+  test("uses the jwks_uri from discovery, so EntraID's key endpoint is reached", async () => {
+    process.env.OIDC_ISSUER_MCP = entraIssuer();
+    process.env.OIDC_AUDIENCE = AUDIENCE;
+    discoveryResponse = {
+      status: 200,
+      // Shape of https://login.microsoftonline.com/{tenant}/v2.0/.well-known/openid-configuration
+      body: JSON.stringify({
+        issuer: entraIssuer(),
+        jwks_uri: `${origin}${entraKeysPath()}`,
+        token_endpoint: `${origin}/${TENANT}/oauth2/v2.0/token`,
+      }),
+    };
+
+    const authenticateBearer = await loadAuthenticateBearer();
+    const claims = await authenticateBearer(`Bearer ${await signAccessToken(entraIssuer())}`);
+
+    expect(claims.sub).toBe("user-object-id");
+    expect(requested).toContain(entraKeysPath());
+    // The Authentik convention must NOT have been tried.
+    expect(requested).not.toContain(`/${TENANT}/v2.0/jwks/`);
+  });
+
+  test("tolerates a trailing slash on the issuer while still honouring discovery", async () => {
+    // acceptedIssuers() takes both spellings; discovery must not regress that.
+    process.env.OIDC_ISSUER_MCP = `${entraIssuer()}/`;
+    process.env.OIDC_AUDIENCE = AUDIENCE;
+    discoveryResponse = {
+      status: 200,
+      body: JSON.stringify({ jwks_uri: `${origin}${entraKeysPath()}` }),
+    };
+
+    const authenticateBearer = await loadAuthenticateBearer();
+    // Token carries the un-slashed spelling; the env var carries the slashed one.
+    const claims = await authenticateBearer(`Bearer ${await signAccessToken(entraIssuer())}`);
+
+    expect(claims.sub).toBe("user-object-id");
+    expect(requested).toContain(entraKeysPath());
+  });
+
+  test("falls back to ${issuer}/jwks/ when discovery is unreachable", async () => {
+    process.env.OIDC_ISSUER_MCP = authentikIssuer();
+    process.env.OIDC_AUDIENCE = AUDIENCE;
+    discoveryResponse = { status: 500, body: "upstream exploded" };
+
+    const authenticateBearer = await loadAuthenticateBearer();
+    const claims = await authenticateBearer(`Bearer ${await signAccessToken(authentikIssuer())}`);
+
+    // Existing Authentik deployments keep working with no discovery document.
+    expect(claims.sub).toBe("user-object-id");
+    expect(requested).toContain("/application/o/shared-memory-mcp/jwks/");
+  });
+
+  test("falls back to ${issuer}/jwks/ when discovery omits jwks_uri", async () => {
+    process.env.OIDC_ISSUER_MCP = authentikIssuer();
+    process.env.OIDC_AUDIENCE = AUDIENCE;
+    // 200 OK, valid JSON, no usable key set pointer — the malformed case that
+    // a naive `doc.jwks_uri` read would turn into `new URL(undefined)`.
+    discoveryResponse = { status: 200, body: JSON.stringify({ issuer: authentikIssuer() }) };
+
+    const authenticateBearer = await loadAuthenticateBearer();
+    const claims = await authenticateBearer(`Bearer ${await signAccessToken(authentikIssuer())}`);
+
+    expect(claims.sub).toBe("user-object-id");
+    expect(requested).toContain("/application/o/shared-memory-mcp/jwks/");
+  });
+
+  test("falls back when discovery returns non-JSON", async () => {
+    process.env.OIDC_ISSUER_MCP = authentikIssuer();
+    process.env.OIDC_AUDIENCE = AUDIENCE;
+    discoveryResponse = { status: 200, body: "<html>login page</html>" };
+
+    const authenticateBearer = await loadAuthenticateBearer();
+    const claims = await authenticateBearer(`Bearer ${await signAccessToken(authentikIssuer())}`);
+
+    expect(claims.sub).toBe("user-object-id");
+    expect(requested).toContain("/application/o/shared-memory-mcp/jwks/");
+  });
+
+  test("discovers once across many verifications, not once per request", async () => {
+    // The MCP endpoint verifies a token on essentially every request. A
+    // discovery fetch per request would add a round-trip to every tool call.
+    process.env.OIDC_ISSUER_MCP = entraIssuer();
+    process.env.OIDC_AUDIENCE = AUDIENCE;
+    discoveryResponse = {
+      status: 200,
+      body: JSON.stringify({ jwks_uri: `${origin}${entraKeysPath()}` }),
+    };
+
+    const authenticateBearer = await loadAuthenticateBearer();
+    for (let i = 0; i < 3; i++) {
+      await authenticateBearer(`Bearer ${await signAccessToken(entraIssuer())}`);
+    }
+
+    expect(discoveryPathsSeen()).toHaveLength(1);
+  });
+
+  test("concurrent cold requests share a single discovery fetch", async () => {
+    // Caching the settled value rather than the in-flight promise would let
+    // every request that arrives before the first one resolves start its own
+    // discovery fetch — a thundering herd at process start.
+    process.env.OIDC_ISSUER_MCP = entraIssuer();
+    process.env.OIDC_AUDIENCE = AUDIENCE;
+    discoveryResponse = {
+      status: 200,
+      body: JSON.stringify({ jwks_uri: `${origin}${entraKeysPath()}` }),
+    };
+
+    const authenticateBearer = await loadAuthenticateBearer();
+    const token = await signAccessToken(entraIssuer());
+    await Promise.all(
+      Array.from({ length: 5 }, () => authenticateBearer(`Bearer ${token}`)),
+    );
+
+    expect(discoveryPathsSeen()).toHaveLength(1);
+  });
+});

apps/web/lib/auth/jwt.ts

@@ -2,13 +2,14 @@ import { createRemoteJWKSet, jwtVerify, errors as joseErrors } from "jose";
 import type { JWTPayload } from "jose";
 import { env } from "@/lib/env";
 import { CLI_TOKEN_KID, tokenKid, verifyCliToken } from "./cli-token";
+import { detectGroupsOverage } from "./sync-groups";
 
 /**
  * Authenticates a bearer token presented to the MCP endpoint. Two token
  * kinds are accepted, dispatched by the JWT `kid` header:
  *
- *   - Authentik-issued OIDC access tokens (any kid) — verified against
- *     Authentik's JWKS over the network.
+ *   - IdP-issued OIDC access tokens (any kid) — verified against the
+ *     issuer's JWKS over the network, located via OIDC discovery.
  *   - CLI tokens minted at /connect (kid="cli-v1") — verified locally
  *     with the HMAC CLI_TOKEN_SECRET.
  *
@@ -18,8 +19,25 @@ import { CLI_TOKEN_KID, tokenKid, verifyCliToken } from "./cli-token";
  * This is distinct from the NextAuth session cookie path used by the Web UI.
  */
 
+type JwkSet = ReturnType<typeof createRemoteJWKSet>;
+
 type GlobalWithJwks = typeof globalThis & {
-  __sharedMemoryJwks?: ReturnType<typeof createRemoteJWKSet>;
+  /**
+   * Resolved key set, cached as a *promise* rather than a value.
+   *
+   * Resolution now involves a network round-trip (OIDC discovery), and the
+   * MCP endpoint verifies a token on essentially every request. Caching the
+   * settled value would leave a window in which N concurrent cold requests
+   * each start their own discovery fetch; caching the in-flight promise means
+   * the first caller does the work and everyone else awaits the same result.
+   */
+  __sharedMemoryJwks?: Promise<JwkSet>;
+  /**
+   * Epoch ms after which discovery should be re-attempted, set only when we
+   * had to fall back (see `jwks()`). Undefined means the cached set came from
+   * a successful discovery and is good indefinitely.
+   */
+  __sharedMemoryJwksRetryAt?: number;
 };
 const g = globalThis as GlobalWithJwks;
 
@@ -27,6 +45,10 @@ const g = globalThis as GlobalWithJwks;
  * Issuer of MCP access tokens. The MCP endpoint is a separate application in
  * the IdP from the Web UI, and Authentik stamps each token with its own
  * application slug, so this is NOT interchangeable with OIDC_ISSUER.
+ *
+ * Not every IdP works that way: EntraID has one issuer per tenant regardless
+ * of how many app registrations you create, so OIDC_ISSUER_MCP is left unset
+ * there and this falls through to OIDC_ISSUER.
  */
 export function mcpIssuer(): string {
   return env().OIDC_ISSUER_MCP ?? env().OIDC_ISSUER;
@@ -50,16 +72,88 @@ function acceptedIssuers(): [string, string] {
   return [bare, `${bare}/`];
 }
 
-function jwks() {
-  if (g.__sharedMemoryJwks) return g.__sharedMemoryJwks;
-  // Authentik discovery is at `${issuer}/.well-known/openid-configuration`;
-  // the JWKS URI is normally `${issuer}/jwks/` or `${issuer}/.well-known/jwks.json`.
-  // Authentik canonically serves `${issuer}/jwks/`.
-  const url = new URL(`${mcpIssuer().replace(/\/$/, "")}/jwks/`);
-  g.__sharedMemoryJwks = createRemoteJWKSet(url, {
-    cacheMaxAge: 10 * 60 * 1000, // 10 min
-    cooldownDuration: 30 * 1000,
-  });
+const JWKS_OPTIONS = {
+  cacheMaxAge: 10 * 60 * 1000, // 10 min
+  cooldownDuration: 30 * 1000,
+} as const;
+
+/** How long to keep serving a fallback key set before retrying discovery. */
+const DISCOVERY_RETRY_COOLDOWN_MS = 60 * 1000;
+
+/** Discovery can hang; every MCP request waits on it, so bound it. */
+const DISCOVERY_TIMEOUT_MS = 5 * 1000;
+
+/**
+ * The pre-discovery convention: `${issuer}/jwks/`.
+ *
+ * This is Authentik's canonical JWKS path and was hardcoded here. It stays as
+ * the fallback so that a deployment whose discovery document is unreachable
+ * behaves exactly as it did before this change.
+ */
+function fallbackJwksUri(): string {
+  return `${mcpIssuer().replace(/\/$/, "")}/jwks/`;
+}
+
+/**
+ * Read `jwks_uri` out of the MCP issuer's OIDC discovery document.
+ *
+ * `${issuer}/jwks/` is an Authentik convention, not a standard — RFC 8414
+ * says the key set lives wherever `jwks_uri` points, and providers disagree
+ * wildly. EntraID serves keys at
+ * `https://login.microsoftonline.com/{tenant}/discovery/v2.0/keys`, nowhere
+ * near `${issuer}/jwks/`, so with the path hardcoded every EntraID-issued MCP
+ * token fails verification with a 404 on the key set — authentication is
+ * simply impossible, not merely misconfigured. Ask the issuer where its keys
+ * are instead of guessing.
+ *
+ * Returns null (never throws) on any failure, so the caller can fall back.
+ */
+async function discoverJwksUri(): Promise<string | null> {
+  const url = `${mcpIssuer().replace(/\/$/, "")}/.well-known/openid-configuration`;
+  try {
+    const res = await fetch(url, {
+      headers: { accept: "application/json" },
+      signal: AbortSignal.timeout(DISCOVERY_TIMEOUT_MS),
+    });
+    if (!res.ok) return null;
+    const doc: unknown = await res.json();
+    const uri = (doc as { jwks_uri?: unknown } | null)?.jwks_uri;
+    if (typeof uri !== "string" || uri.trim().length === 0) return null;
+    // A malformed jwks_uri must not blow up the request path.
+    new URL(uri);
+    return uri;
+  } catch {
+    return null;
+  }
+}
+
+/**
+ * The key set MCP access tokens are verified against, resolved once per
+ * process.
+ *
+ * Async because discovery is a network call. The cached promise is installed
+ * synchronously — before the first `await` inside the IIFE runs — so
+ * concurrent callers always join the existing resolution rather than racing
+ * to start their own.
+ *
+ * When discovery fails we serve the legacy fallback but arm a retry: a single
+ * blip at process start would otherwise pin the wrong URL for the lifetime of
+ * the container, which on EntraID means MCP auth stays broken until someone
+ * restarts it. The cooldown keeps a persistently-unreachable discovery
+ * endpoint from being hit on every request.
+ */
+function jwks(): Promise<JwkSet> {
+  const retryAt = g.__sharedMemoryJwksRetryAt;
+  const dueForRetry = retryAt !== undefined && Date.now() >= retryAt;
+  if (g.__sharedMemoryJwks && !dueForRetry) return g.__sharedMemoryJwks;
+
+  g.__sharedMemoryJwksRetryAt = undefined;
+  g.__sharedMemoryJwks = (async () => {
+    const discovered = await discoverJwksUri();
+    if (discovered) return createRemoteJWKSet(new URL(discovered), JWKS_OPTIONS);
+    g.__sharedMemoryJwksRetryAt = Date.now() + DISCOVERY_RETRY_COOLDOWN_MS;
+    return createRemoteJWKSet(new URL(fallbackJwksUri()), JWKS_OPTIONS);
+  })();
   return g.__sharedMemoryJwks;
 }
 
@@ -143,7 +237,7 @@ export async function authenticateBearer(authHeader: string | null): Promise<Aut
       } as AuthenticatedClaims;
     }
 
-    const { payload } = await jwtVerify(token, jwks(), {
+    const { payload } = await jwtVerify(token, await jwks(), {
       issuer: acceptedIssuers(),
       audience: env().OIDC_AUDIENCE,
     });
@@ -153,6 +247,17 @@ export async function authenticateBearer(authHeader: string | null): Promise<Aut
         buildWwwAuthenticate("invalid_token", "missing sub"),
       );
     }
+    // Groups overage: the IdP is telling us it holds memberships it declined
+    // to list. `extractGroupsClaim` would read that as "no claim emitted" and
+    // userContextFromClaims would fall back to the DB snapshot — granting
+    // project access from a stale record while the live state is admittedly
+    // unknown. Refuse; the operator fix is in the description.
+    if (detectGroupsOverage(payload)) {
+      const desc =
+        "groups overage: IdP did not enumerate group membership " +
+        "(set groupMembershipClaims=ApplicationGroup on EntraID)";
+      throw new UnauthorizedError(desc, buildWwwAuthenticate("invalid_token", desc));
+    }
     // Normalize the issuer for identity purposes.
     //
     // The token was just verified against mcpIssuer() — that check is done.

apps/web/lib/auth/sync-groups.test.ts

@@ -0,0 +1,126 @@
+import { afterAll, beforeEach, describe, expect, test } from "vitest";
+
+/**
+ * Group sync, and specifically the overage case.
+ *
+ * `syncUserGroupsFromClaim` deletes every membership when it sees no groups.
+ * That is correct for "the IdP says zero groups" and catastrophic for "the
+ * IdP declined to enumerate them" — EntraID past 200 groups. The two look
+ * identical if you only inspect `claims.groups`, which is why the function
+ * takes the whole claims object.
+ */
+const { db, pg } = await import("@/lib/db/client");
+const { users, groups, userGroups } = await import("@/lib/db/schema");
+const { syncUserGroupsFromClaim, detectGroupsOverage, GroupsOverageError } =
+  await import("@/lib/auth/sync-groups");
+const { eq } = await import("drizzle-orm");
+
+const ISS = "https://login.microsoftonline.com/sync-test/v2.0";
+let userId: string;
+
+async function memberships(): Promise<string[]> {
+  const rows = await db
+    .select({ name: groups.name })
+    .from(userGroups)
+    .innerJoin(groups, eq(userGroups.groupId, groups.id))
+    .where(eq(userGroups.userId, userId));
+  return rows.map((r) => r.name).sort();
+}
+
+beforeEach(async () => {
+  await db.delete(users).where(eq(users.oidcIss, ISS));
+  await db.delete(groups).where(eq(groups.oidcIss, ISS));
+  const rows = await db
+    .insert(users)
+    .values({ oidcIss: ISS, oidcSub: "sync-test-sub" })
+    .returning({ id: users.id });
+  const row = rows[0];
+  if (!row) throw new Error("failed to seed test user");
+  userId = row.id;
+});
+
+afterAll(async () => {
+  await db.delete(users).where(eq(users.oidcIss, ISS));
+  await db.delete(groups).where(eq(groups.oidcIss, ISS));
+  await pg.end();
+});
+
+describe("detectGroupsOverage", () => {
+  test("spots the JWT overage pointer", () => {
+    expect(
+      detectGroupsOverage({
+        _claim_names: { groups: "src1" },
+        _claim_sources: { src1: { endpoint: "https://graph.windows.net/x" } },
+      }),
+    ).toBe(true);
+  });
+
+  test("spots the implicit-flow indicator", () => {
+    expect(detectGroupsOverage({ hasgroups: true })).toBe(true);
+  });
+
+  test("is false for ordinary claims", () => {
+    expect(detectGroupsOverage({ groups: ["a"] })).toBe(false);
+    expect(detectGroupsOverage({})).toBe(false);
+    expect(detectGroupsOverage(null)).toBe(false);
+    // A _claim_names for some OTHER claim is not a groups overage.
+    expect(detectGroupsOverage({ _claim_names: { roles: "src1" } })).toBe(false);
+    expect(detectGroupsOverage({ hasgroups: false })).toBe(false);
+  });
+});
+
+describe("syncUserGroupsFromClaim", () => {
+  test("stores the claim's names", async () => {
+    await syncUserGroupsFromClaim(userId, ISS, { groups: ["eng", "ops"] });
+    expect(await memberships()).toEqual(["eng", "ops"]);
+  });
+
+  test("an empty claim really does clear memberships", async () => {
+    await syncUserGroupsFromClaim(userId, ISS, { groups: ["eng"] });
+    await syncUserGroupsFromClaim(userId, ISS, { groups: [] });
+    expect(await memberships()).toEqual([]);
+  });
+
+  test("an absent claim clears memberships", async () => {
+    // Unchanged behaviour: the IdP has stopped asserting groups, so we stop
+    // honouring them rather than keeping stale grants alive.
+    await syncUserGroupsFromClaim(userId, ISS, { groups: ["eng"] });
+    await syncUserGroupsFromClaim(userId, ISS, {});
+    expect(await memberships()).toEqual([]);
+  });
+
+  test("overage throws instead of clearing", async () => {
+    await syncUserGroupsFromClaim(userId, ISS, { groups: ["eng", "ops"] });
+
+    await expect(
+      syncUserGroupsFromClaim(userId, ISS, {
+        _claim_names: { groups: "src1" },
+        _claim_sources: { src1: { endpoint: "https://graph.windows.net/x" } },
+      }),
+    ).rejects.toBeInstanceOf(GroupsOverageError);
+
+    // The whole point: the snapshot survives, so the operator can fix the IdP
+    // and the user comes back with their access intact.
+    expect(await memberships()).toEqual(["eng", "ops"]);
+  });
+
+  test("the overage error names the fix", async () => {
+    let err: Error | null = null;
+    try {
+      await syncUserGroupsFromClaim(userId, ISS, { hasgroups: true });
+    } catch (e) {
+      err = e as Error;
+    }
+
+    expect(err).toBeInstanceOf(GroupsOverageError);
+    expect(err?.message).toContain("groupMembershipClaims");
+    expect(err?.message).toContain("ApplicationGroup");
+  });
+
+  test("non-string entries are dropped, names are de-duplicated", async () => {
+    await syncUserGroupsFromClaim(userId, ISS, {
+      groups: ["eng", 7, null, " eng ", "ops"],
+    });
+    expect(await memberships()).toEqual(["eng", "ops"]);
+  });
+});

apps/web/lib/auth/sync-groups.ts

@@ -2,34 +2,99 @@ import { and, eq, notInArray, sql } from "drizzle-orm";
 import { db } from "@/lib/db/client";
 import { groups, userGroups } from "@/lib/db/schema";
 
+/**
+ * Raised when the IdP signals that it holds group memberships it declined to
+ * enumerate (EntraID's "groups overage"). Callers must abort — see
+ * `detectGroupsOverage` for why this cannot be treated as "no groups".
+ */
+export class GroupsOverageError extends Error {
+  constructor() {
+    super(
+      "OIDC groups overage: the identity provider signalled group membership " +
+        "it did not enumerate, so the user's groups cannot be determined. On " +
+        "EntraID, set the app registration's `groupMembershipClaims` to " +
+        '"ApplicationGroup" (portal: "Groups assigned to the application") and ' +
+        "assign the groups you share projects with. See docs/oidc-entra-id.md " +
+        "§10b.",
+    );
+    this.name = "GroupsOverageError";
+  }
+}
+
+/**
+ * Does this token say "there are groups, but I'm not listing them"?
+ *
+ * EntraID stops emitting `groups` past 200 entries in a JWT (150 in SAML, 5 in
+ * implicit flow) and substitutes a pointer:
+ *
+ *     "_claim_names":   { "groups": "src1" },
+ *     "_claim_sources": { "src1": { "endpoint": "https://graph.windows.net/…" } }
+ *
+ * or, for implicit flow, `"hasgroups": true`.
+ *
+ * This is NOT a truncated list — it is no list at all, and it is materially
+ * different from "this user belongs to zero groups". Conflating the two is
+ * what made this dangerous: the absent-claim branch below deletes every one of
+ * the user's memberships, so a user crossing the 200-group line would silently
+ * lose access to every shared project on both surfaces, with no error raised
+ * anywhere.
+ *
+ * We refuse instead. Group state gates `readableProjectIds` / `canWriteProject`,
+ * and granting or revoking access on state we know we don't have is guesswork
+ * either way. Failing loudly destroys nothing and names its own fix.
+ */
+export function detectGroupsOverage(claims: unknown): boolean {
+  const c = claims as
+    | { _claim_names?: unknown; hasgroups?: unknown }
+    | null
+    | undefined;
+  if (!c || typeof c !== "object") return false;
+  if (c.hasgroups === true) return true;
+  const names = c._claim_names;
+  return (
+    typeof names === "object" &&
+    names !== null &&
+    "groups" in (names as Record<string, unknown>)
+  );
+}
+
 /**
  * Sync a user's group memberships from the OIDC `groups` claim on sign-in.
  *
+ * Takes the whole claims object, not just the claim value, because deciding
+ * what an absent `groups` means requires seeing the overage markers that sit
+ * beside it.
+ *
  * Claim shape: `string[]`. Authentik emits group *names* directly here;
- * Keycloak and Okta likewise (with the right mappers configured). EntraID,
- * when correctly configured per README, emits names too — but the default
- * "groups" optional-claim variant emits object-id GUIDs instead, and if the
- * user is in too many groups EntraID switches to a "groups overage"
- * indicator (no group list at all). We take the conservative path:
+ * Keycloak and Okta likewise (with the right mappers configured). EntraID
+ * emits object-id GUIDs by default — `cloud_displayname` gets you names, but
+ * only under `groupMembershipClaims: "ApplicationGroup"`, and only for
+ * directly assigned groups. See docs/oidc-entra-id.md §10a.
  *
  *   - whatever strings appear in the claim are treated as names verbatim
  *     and stored as-is. If your IdP emits GUIDs, the UI will show GUIDs;
  *     fix it at the IdP layer (we don't attempt resolution).
  *   - if the claim is missing/empty, the user is treated as having zero
- *     groups and all existing memberships are deleted.
- *   - groups overage (where EntraID emits `_claim_names.groups` instead of
- *     `groups`) is not handled in v1 — the user appears as having no
- *     groups. Documented limit; revisit if it bites someone.
+ *     groups and all existing memberships are deleted. That is the
+ *     conservative reading: don't keep stale grants alive once the IdP has
+ *     stopped asserting them.
+ *   - if the IdP signals an overage, we throw rather than apply either
+ *     reading. See `detectGroupsOverage`.
  *
  * The whole operation runs in a single transaction so the membership
  * snapshot is atomic (no window where a user partially has new memberships
  * and still has stale ones).
+ *
+ * @throws {GroupsOverageError} when the claims carry an overage indicator.
  */
 export async function syncUserGroupsFromClaim(
   userId: string,
   oidcIss: string,
-  rawClaim: unknown,
+  claims: unknown,
 ): Promise<void> {
+  if (detectGroupsOverage(claims)) throw new GroupsOverageError();
+
+  const rawClaim = (claims as { groups?: unknown } | null | undefined)?.groups;
   const names = normalizeGroupsClaim(rawClaim);
 
   await db.transaction(async (tx) => {

apps/web/lib/db/schema.ts

@@ -53,6 +53,21 @@ export const users = pgTable(
     oidcSub: text("oidc_sub").notNull(),
     // OIDC `iss` so we can disambiguate if we ever federate.
     oidcIss: text("oidc_iss").notNull(),
+    /**
+     * EntraID `oid` — the user's directory object id.
+     *
+     * Null on IdPs that don't emit it (Authentik, Keycloak, Okta), where
+     * `sub` is already stable across applications and remains the key.
+     *
+     * EntraID's `sub` is PAIRWISE: it is derived from the token recipient,
+     * so the Web UI app registration and the MCP app registration produce
+     * different `sub` values for the same human. Keying on `sub` there
+     * silently creates two accounts for one person — sign in on the web,
+     * connect an MCP client, find an empty account. `oid` is the identifier
+     * Microsoft documents as constant for a user across every application in
+     * a tenant, so it takes precedence whenever it's present.
+     */
+    oidcOid: text("oidc_oid"),
     email: text("email"),
     name: text("name"),
     picture: text("picture"),
@@ -61,6 +76,11 @@ export const users = pgTable(
   },
   (t) => ({
     uniqueIss: uniqueIndex("users_iss_sub_uq").on(t.oidcIss, t.oidcSub),
+    // Partial: rows from IdPs that emit no `oid` all hold NULL here, and a
+    // plain unique index would collapse them into a single allowed row.
+    uniqueOid: uniqueIndex("users_iss_oid_uq")
+      .on(t.oidcIss, t.oidcOid)
+      .where(sql`${t.oidcOid} IS NOT NULL`),
   }),
 );
 

apps/web/lib/mcp/context.ts

@@ -1,6 +1,7 @@
 import { db } from "@/lib/db/client";
-import { users, groups, userGroups } from "@/lib/db/schema";
-import { and, eq } from "drizzle-orm";
+import { groups, userGroups } from "@/lib/db/schema";
+import { eq } from "drizzle-orm";
+import { oidClaim, resolveUserId } from "@/lib/auth/identity";
 import type { AuthenticatedClaims } from "@/lib/auth/jwt";
 
 /**
@@ -55,37 +56,18 @@ export async function userContextFromClaims(
   const name = (claims.name as string | undefined) ?? null;
   const picture = (claims.picture as string | undefined) ?? null;
 
-  const row = await db
-    .insert(users)
-    .values({
-      oidcSub: claims.sub,
-      oidcIss: claims.iss,
-      email,
-      name,
-      picture,
-    })
-    .onConflictDoUpdate({
-      target: [users.oidcIss, users.oidcSub],
-      set: {
-        email,
-        name,
-        picture,
-        lastSeenAt: new Date(),
-      },
-    })
-    .returning({ id: users.id });
-
-  let userId = row[0]?.id;
-  if (!userId) {
-    // Race against another upsert — fall back to a select.
-    const existing = await db
-      .select({ id: users.id })
-      .from(users)
-      .where(and(eq(users.oidcIss, claims.iss), eq(users.oidcSub, claims.sub)))
-      .limit(1);
-    if (!existing[0]) throw new Error("user upsert failed and not found on re-read");
-    userId = existing[0].id;
-  }
+  // Shared with the Web UI sign-in path (auth.ts). Keeping one resolver is
+  // what stops the two surfaces disagreeing about who a user is — on EntraID
+  // they see different `sub` values for the same person and would otherwise
+  // each create their own account. See lib/auth/identity.ts.
+  const userId = await resolveUserId({
+    iss: claims.iss,
+    sub: claims.sub,
+    oid: oidClaim(claims),
+    email,
+    name,
+    picture,
+  });
 
   // OIDC bearer tokens carry a `groups` claim (when the IdP is configured to
   // emit it). CLI tokens never do — they go through verifyCliToken which