Close search's active-tenant write-routing gap with a polled allowlist
search/src/consumer.rs's write-routing (built last pass) had no active- tenant check at all: IndexRegistry.resolve() would open-or-create an index directory for any syntactically-valid tenant_id, active or not -- unlike ClickHouse's chwriter.Registry (an active-tenants-only snapshot built at enterprise-ingest startup) or the read side (gated by searchclient.TenantChecker, a direct rbacstore query). search is AGPL core with no Postgres access and no enterprise/ import allowed, so it needed a network boundary instead -- the same shape ingest's TenantResolver already uses against enterprise-auth, just Rust calling Go instead of Go calling Go. New GET /internal/active-tenants endpoint on enterprise-auth (rbacstore.ListActiveTenantIDs + authhandler.handleActiveTenants), gated on a RoleService Bearer credential -- server-to-server auth, the same shape alerting presents to api, minted via the already-generic enterprise-auth -mint-service-token search. search/src/tenants.rs's ActiveTenantTracker polls it every 60s, blocking startup on the first fetch succeeding (fail-closed cold start -- a control-plane outage at boot must not silently accept every tenant_id) and keeping the last- known-good set on any later refresh failure (a transient blip shouldn't stop every tenant's indexing, only prevent the allowlist from growing/ shrinking until connectivity resumes). consumer.rs refuses any tagged record whose tenant isn't in the polled set, before ever calling resolve() -- IndexRegistry itself stays policy-free, matching the same mechanism/policy split clickhousewriter.Writer vs. chwriter.Registry already draws on the ClickHouse side. Off unless ENTERPRISE_AUTH_URL/ENTERPRISE_AUTH_SERVICE_TOKEN are both set (search/src/config.rs rejects exactly one being set) -- every existing deployment is unaffected. Verified with real HTTP round trips in this environment: tenants.rs's tests exercise real reqwest requests (actual Authorization: Bearer header, actual JSON parsing) against a hand-rolled dependency-free TCP test server, including both fail-closed paths (rejected first fetch, unreachable server). authhandler's new tests cover the credential-kind distinction this endpoint exists to enforce -- a real human session, even for a genuine Owner, must not satisfy a check meant for a service identity. One asymmetry remains, disclosed rather than fixed: chwriter.Registry's snapshot still never refreshes (stale until enterprise-ingest restarts), while ActiveTenantTracker's 60s poll gives Tantivy a materially tighter staleness window. Neither is a live per-write check -- that would mean a database/HTTP round trip per record, a throughput cost neither implementation accepts -- so both have some staleness window by design; the gap between the two windows is what's disclosed, not a claim either is fully live.
This commit is contained in:
@@ -198,6 +198,34 @@ func (s *Store) TenantIsActive(ctx context.Context, tenantID string) (bool, erro
|
||||
return t.Status == "active", nil
|
||||
}
|
||||
|
||||
// ListActiveTenantIDs backs enterprise-auth's GET /internal/active-tenants
|
||||
// -- search (AGPL core) polls this to learn which tenant_ids it may
|
||||
// safely write-route into their own Tantivy index, since it has no
|
||||
// Postgres access of its own (see search/src/tenants.rs's doc comment
|
||||
// for the full design). Deliberately narrower than
|
||||
// ListProvisionedDataSources (which also requires ClickHouse
|
||||
// credentials to be present, since chwriter.Registry needs those to
|
||||
// actually connect): search's write path needs nothing but the id.
|
||||
func (s *Store) ListActiveTenantIDs(ctx context.Context) ([]string, error) {
|
||||
rows, err := s.pool.Query(ctx, `SELECT id FROM tenants WHERE status = 'active'`)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("rbacstore: listing active tenant ids: %w", err)
|
||||
}
|
||||
defer rows.Close()
|
||||
var ids []string
|
||||
for rows.Next() {
|
||||
var id string
|
||||
if err := rows.Scan(&id); err != nil {
|
||||
return nil, fmt.Errorf("rbacstore: scanning active tenant id: %w", err)
|
||||
}
|
||||
ids = append(ids, id)
|
||||
}
|
||||
if err := rows.Err(); err != nil {
|
||||
return nil, fmt.Errorf("rbacstore: iterating active tenant ids: %w", err)
|
||||
}
|
||||
return ids, nil
|
||||
}
|
||||
|
||||
// SetTenantStatus is the only way a tenant's status column changes --
|
||||
// every tenant-resolution path elsewhere must re-check this via
|
||||
// GetTenant, never cache/assume 'active', per
|
||||
|
||||
@@ -470,6 +470,41 @@ func createTestDashboard(t *testing.T, s *Store, tenantID, createdBy string) str
|
||||
return id
|
||||
}
|
||||
|
||||
func TestListActiveTenantIDsExcludesNonActive(t *testing.T) {
|
||||
s := testStore(t)
|
||||
ctx := context.Background()
|
||||
|
||||
active := "test-tenant-" + uniqueSuffix()
|
||||
provisioning := "test-tenant-" + uniqueSuffix()
|
||||
|
||||
for _, id := range []string{active, provisioning} {
|
||||
if _, err := s.CreateTenant(ctx, id, id); err != nil {
|
||||
t.Fatalf("CreateTenant %s: %v", id, err)
|
||||
}
|
||||
}
|
||||
if err := s.SetTenantStatus(ctx, active, "active"); err != nil {
|
||||
t.Fatalf("SetTenantStatus active: %v", err)
|
||||
}
|
||||
// provisioning stays in 'provisioning' (CreateTenant's default).
|
||||
|
||||
ids, err := s.ListActiveTenantIDs(ctx)
|
||||
if err != nil {
|
||||
t.Fatalf("ListActiveTenantIDs: %v", err)
|
||||
}
|
||||
foundActive := false
|
||||
for _, id := range ids {
|
||||
if id == provisioning {
|
||||
t.Fatalf("non-active tenant %q leaked into ListActiveTenantIDs", provisioning)
|
||||
}
|
||||
if id == active {
|
||||
foundActive = true
|
||||
}
|
||||
}
|
||||
if !foundActive {
|
||||
t.Fatal("expected the active tenant to be in the list")
|
||||
}
|
||||
}
|
||||
|
||||
func TestSetDashboardPermissionThenGet(t *testing.T) {
|
||||
s := testStore(t)
|
||||
ctx := context.Background()
|
||||
|
||||
Reference in New Issue
Block a user