mirror of
https://github.com/shankar0123/certctl.git
synced 2026-06-07 14:51:30 +00:00
3ef45e2ad4
# Phase 6 — day-0 admin bootstrap * internal/auth/bootstrap/ (new package): Strategy interface + EnvTokenStrategy with constant-time compare, one-shot consumption via sync.Mutex, optional admin-existence probe. Bundle 2's OIDC- first-admin will plug in alongside as an alternate Strategy. * BootstrapService.ValidateAndMint: validates the operator's CERTCTL_BOOTSTRAP_TOKEN, mints a 32-byte (64-hex-char) random API key value, persists the SHA-256 hash to api_keys, grants r-admin via actor_roles, AddHashed's the runtime keystore so the just- minted key authenticates the next request without restart, and records bootstrap.consume to the audit trail with category=auth. * internal/auth/keystore.go (new): KeyStore interface + StaticKeyStore (immutable env-var-only path) + MutableKeyStore (env-var keys + DB-loaded api_keys + runtime AddHashed). The auth middleware now consumes a KeyStore so the bootstrap path can extend the lookup table at runtime. * migrations/000031_api_keys.up/down.sql: api_keys table with (id, name UNIQUE, key_hash UNIQUE, tenant_id, admin, created_by, created_at, expires_at, last_used_at). Idempotent. * /v1/auth/bootstrap GET (probe) + POST (mint) — auth-exempt. Both routes documented in api/openapi.yaml + AuthExemptRouterRoutes allowlist updated. The token never leaves internal/auth/bootstrap; the minted plaintext key flows only into the HTTP response body. * Startup warning emitted when CERTCTL_BOOTSTRAP_TOKEN is set AND admin actors already exist (config drift signal). * Tests: 4 strategy invariants (empty token born disabled, wrong token=ErrInvalidToken without consumption, one-shot consumption, admin-exists closes path), 5 service tests (happy path + actor- name validation + propagation of strategy errors + nil-deps guard + 32-byte entropy budget), 8 HTTP-handler tests (status 201/410/401/400 mapping + token-leak hygiene scan of slog + audit details + Location header). Token-leak test redirects slog.Default to a buffer for the test scope. # Phase 7 — API-key migration + scope-down CLI * GET /v1/auth/keys handler + service method ListKeys backed by ActorRoleRepository.ListDistinctActors. Returns one row per (actor_id, actor_type) pair with the slice of role IDs they hold. Permission: auth.role.list. * internal/cli/auth_scope_down.go: AuthListKeys, AuthScopeDown (interactive), AuthScopeDownNonInteractive (JSON config), AuthScopeDownSuggest (--suggest with optional --apply). The synthetic actor-demo-anon is filtered out of every interactive / bulk path; non-interactive flow logs and skips it explicitly. * SuggestRoleFromAuditEvents (pure function): walks 30 days of audit events per actor and returns the narrowest matching role (admin / mcp / viewer / agent / operator) plus a one-line reason. Classification: any admin-shaped action wins; otherwise all-MCP → mcp; all-read-only → viewer; all-agent-shaped → agent; otherwise operator. Test table pins all six classifications. * CLI subcommand tree extended: 'auth keys list' + 'auth keys scope-down [--non-interactive <cfg>] [--suggest [--apply]]'. * CHANGELOG.md leads v2.1.0 with the SECURITY: AUDIT YOUR API KEYS call-out + four flow examples. # Phase 8 — auditor role + event_category column * migrations/000032_audit_category.up/down.sql: ALTER TABLE audit_events ADD COLUMN event_category TEXT NOT NULL DEFAULT 'cert_lifecycle' + CHECK constraint (cert_lifecycle/auth/config) + (event_category) and (event_category, timestamp DESC) indexes for the auditor-filter query path. WORM trigger from migration 000018 continues to enforce append-only at the DB layer (DDL is not blocked). * domain.AuditEvent gains EventCategory string (omitempty); domain.EventCategoryCertLifecycle / Auth / Config constants. * AuditService.RecordEventWithCategory sibling of RecordEvent; legacy callers stay on RecordEvent (defaults to cert_lifecycle). Auth callers (RoleService, ActorRoleService, BootstrapService) switched to RecordEventWithCategory(..., 'auth', ...). * GET /v1/audit?category=<cat>: handler accepts the optional query param, validates against the enum (400 on invalid value), dispatches through ListAuditEventsByCategory. OpenAPI updated with the new query param + AuditEvent.event_category schema. * Postgres AuditRepository.Create now writes event_category; AuditRepository.List filters on it; AuditFilter.EventCategory gates the WHERE clause. * Tests: 5 audit-category-filter HTTP tests (dispatch routing, back-compat fallback, 400 for invalid values, all 3 enum values accepted, page+category combine, JSON output surfaces the field). 3 auditor-role invariants (auditor holds exactly audit.read+audit.export, no mutating perms, disjoint from viewer except audit.read). # Cross-phase wiring * HandlerRegistry.Bootstrap field added; cmd/server/main.go wires the bootstrap service ahead of RegisterHandlers (extracted assembleNamedAPIKeys helper into auth_backfill.go, moved the keystore + bootstrap construction up alongside the auth repos). * AuthCheckResolver / AuthActorRoleService extended with ListKeys to satisfy the Phase 7 surface; existing fakes updated. * fakeAudit + mockAuditService stubs in tests gain RecordEventWithCategory + ListAuditEventsByCategory; existing tests untouched. # Verifications * gofmt -l: clean across every modified file. * go vet ./...: clean. * staticcheck across internal/auth + handler + router + cli + service + repository + cmd + domain: clean. * go test -short -count=1: green across every Bundle-1-touched package — internal/auth (incl. bootstrap), internal/api/handler, internal/api/router, internal/cli, internal/service/auth, internal/service, internal/domain/auth, internal/repository/postgres, cmd/server, cmd/cli, plus internal/scheduler, internal/api/middleware, cmd/agent, internal/mcp.
126 lines
5.2 KiB
Go
126 lines
5.2 KiB
Go
package bootstrap
|
|
|
|
import (
|
|
"context"
|
|
"errors"
|
|
"testing"
|
|
)
|
|
|
|
// TestEnvTokenStrategy_EmptyTokenIsBornDisabled pins the load-bearing
|
|
// invariant that an unset CERTCTL_BOOTSTRAP_TOKEN closes the bootstrap
|
|
// path at construction time. The handler depends on this — without it,
|
|
// a misconfigured deploy that forgot to set the env var would expose
|
|
// the endpoint with a token of "" that an attacker could trivially
|
|
// match by also sending "".
|
|
func TestEnvTokenStrategy_EmptyTokenIsBornDisabled(t *testing.T) {
|
|
s := NewEnvTokenStrategy("", nil)
|
|
avail, err := s.Available(context.Background())
|
|
if err != nil {
|
|
t.Fatalf("Available err = %v, want nil", err)
|
|
}
|
|
if avail {
|
|
t.Errorf("Available = true for empty token, want false")
|
|
}
|
|
if got := s.Validate(context.Background(), ""); !errors.Is(got, ErrDisabled) {
|
|
t.Errorf("Validate('') for empty-token strategy = %v, want ErrDisabled", got)
|
|
}
|
|
if got := s.Validate(context.Background(), "anything"); !errors.Is(got, ErrDisabled) {
|
|
t.Errorf("Validate('anything') for empty-token strategy = %v, want ErrDisabled", got)
|
|
}
|
|
}
|
|
|
|
// TestEnvTokenStrategy_WrongTokenReturnsInvalidToken pins that the
|
|
// strategy maps a token mismatch to ErrInvalidToken (HTTP 401), not
|
|
// ErrDisabled (410). Misclassifying these would let a probing attacker
|
|
// distinguish "no token set" from "wrong token" via response status.
|
|
func TestEnvTokenStrategy_WrongTokenReturnsInvalidToken(t *testing.T) {
|
|
s := NewEnvTokenStrategy("correct-token", nil)
|
|
if got := s.Validate(context.Background(), "wrong-token"); !errors.Is(got, ErrInvalidToken) {
|
|
t.Errorf("Validate(wrong) = %v, want ErrInvalidToken", got)
|
|
}
|
|
if got := s.Validate(context.Background(), ""); !errors.Is(got, ErrInvalidToken) {
|
|
t.Errorf("Validate('') = %v, want ErrInvalidToken", got)
|
|
}
|
|
if s.IsConsumed() {
|
|
t.Errorf("strategy consumed after failed Validate; must remain available for retry")
|
|
}
|
|
}
|
|
|
|
// TestEnvTokenStrategy_OneShotConsumption pins the invariant that the
|
|
// first valid Validate call locks the strategy. The bootstrap path is
|
|
// strictly one-shot; the second call MUST return ErrDisabled (HTTP
|
|
// 410), not ErrInvalidToken (which would suggest "wrong token, try
|
|
// again").
|
|
func TestEnvTokenStrategy_OneShotConsumption(t *testing.T) {
|
|
s := NewEnvTokenStrategy("correct-token", nil)
|
|
if err := s.Validate(context.Background(), "correct-token"); err != nil {
|
|
t.Fatalf("first Validate = %v, want nil", err)
|
|
}
|
|
if !s.IsConsumed() {
|
|
t.Errorf("IsConsumed = false after successful Validate, want true")
|
|
}
|
|
if got := s.Validate(context.Background(), "correct-token"); !errors.Is(got, ErrDisabled) {
|
|
t.Errorf("second Validate = %v, want ErrDisabled", got)
|
|
}
|
|
avail, err := s.Available(context.Background())
|
|
if err != nil {
|
|
t.Fatalf("Available err = %v", err)
|
|
}
|
|
if avail {
|
|
t.Errorf("Available = true after consumption, want false")
|
|
}
|
|
}
|
|
|
|
// TestEnvTokenStrategy_AdminExistsClosesPath pins the invariant that
|
|
// the admin-existence probe gates Available + Validate. The strategy
|
|
// must NOT mint a second admin even if the operator forgot to unset
|
|
// CERTCTL_BOOTSTRAP_TOKEN after onboarding.
|
|
func TestEnvTokenStrategy_AdminExistsClosesPath(t *testing.T) {
|
|
probe := func(_ context.Context) (bool, error) { return true, nil }
|
|
s := NewEnvTokenStrategy("correct-token", probe)
|
|
avail, err := s.Available(context.Background())
|
|
if err != nil {
|
|
t.Fatalf("Available err = %v", err)
|
|
}
|
|
if avail {
|
|
t.Errorf("Available = true with admin exists probe, want false")
|
|
}
|
|
if got := s.Validate(context.Background(), "correct-token"); !errors.Is(got, ErrDisabled) {
|
|
t.Errorf("Validate = %v with admin exists, want ErrDisabled", got)
|
|
}
|
|
if s.IsConsumed() {
|
|
t.Errorf("strategy must NOT be consumed when admin-existence probe rejects; allows retry after operator removes the duplicate admin")
|
|
}
|
|
}
|
|
|
|
// TestEnvTokenStrategy_AdminProbeError surfaces the error to the
|
|
// caller without consuming the strategy. The HTTP handler maps this
|
|
// to 500; the operator can retry once the underlying issue is fixed.
|
|
func TestEnvTokenStrategy_AdminProbeError(t *testing.T) {
|
|
probeErr := errors.New("boom")
|
|
probe := func(_ context.Context) (bool, error) { return false, probeErr }
|
|
s := NewEnvTokenStrategy("correct-token", probe)
|
|
if _, err := s.Available(context.Background()); !errors.Is(err, probeErr) {
|
|
t.Errorf("Available err = %v, want probeErr", err)
|
|
}
|
|
if got := s.Validate(context.Background(), "correct-token"); !errors.Is(got, probeErr) {
|
|
t.Errorf("Validate err = %v, want probeErr", got)
|
|
}
|
|
if s.IsConsumed() {
|
|
t.Errorf("strategy must NOT be consumed on probe error")
|
|
}
|
|
}
|
|
|
|
// TestEnvTokenStrategy_ZeroLengthRejectedEvenWithMatchingToken belt-
|
|
// and-braces against the ConstantTimeCompare("","")=1 footgun. A
|
|
// strategy explicitly constructed with token="" is born disabled
|
|
// (ErrDisabled); but if a future caller bypasses the constructor, the
|
|
// Validate path also rejects zero-length tokens up front.
|
|
func TestEnvTokenStrategy_ZeroLengthRejectedEvenWithMatchingToken(t *testing.T) {
|
|
// Directly construct a strategy with token=""
|
|
s := &EnvTokenStrategy{token: "", tokenLength: 0, consumed: false}
|
|
if got := s.Validate(context.Background(), ""); !errors.Is(got, ErrInvalidToken) {
|
|
t.Errorf("Validate('','') = %v, want ErrInvalidToken (zero-length guard)", got)
|
|
}
|
|
}
|