mirror of
https://github.com/shankar0123/certctl.git
synced 2026-06-12 00:38:53 +00:00
fix: end-to-end certificate lifecycle bugs + integration test environment
Fixes 12 production bugs preventing the full issuance→deployment flow from working with ACME (Pebble/Let's Encrypt) and step-ca issuers: ACME connector (acme.go): - Save orderURI before WaitOrder overwrites it (Go crypto/acme bug) - Add CreateOrderCert fallback via WaitOrder+FetchCert - Remove defer-reset in ValidateConfig that caused nil pointer panic - Add Insecure TLS option for self-signed ACME servers (Pebble) step-ca connector (stepca.go, jwe.go): - Real JWE provisioner key loading + decryption (was using ephemeral keys) - Fix JWT audience (/1.0/sign), sha claim (key fingerprint), kid header - Custom root CA trust via RootCertPath config - Remove hardcoded 90-day validity default (let step-ca decide) NGINX target connector (nginx.go): - Use sh -c for validate/reload commands (shell interpretation) - Use filepath.Dir instead of fragile string slicing - Add private key file writing (agent-mode keys were never deployed) - Make chain_path write conditional Server/service layer: - TriggerRenewalWithActor now creates actual Job records (was no-op) - createDeploymentJobs falls back to DB query when cert.TargetIDs empty - ProcessPendingJobs skips agent-routed deployment jobs - Agent cert pickup path parsing: len(parts)<4 → len(parts)<3 - Health/ready/auth-info endpoints bypass auth middleware - Write timeout 15s→120s for ACME issuance - Cert fingerprint computed on CSR submission Integration test environment (deploy/test/): - 10-phase test script covering Local CA, ACME, step-ca, revocation, discovery, renewal, and API spot checks - Docker Compose with 7 containers (server, agent, postgres, nginx, pebble, challtestsrv, step-ca) on isolated network - TLS verification checks SAN (not just Subject CN) for modern CA compat Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -14,10 +14,12 @@ import (
|
||||
type CertificateService struct {
|
||||
certRepo repository.CertificateRepository
|
||||
targetRepo repository.TargetRepository
|
||||
jobRepo repository.JobRepository
|
||||
policyService *PolicyService
|
||||
auditService *AuditService
|
||||
revSvc *RevocationSvc
|
||||
caSvc *CAOperationsSvc
|
||||
keygenMode string
|
||||
}
|
||||
|
||||
// NewCertificateService creates a new certificate service.
|
||||
@@ -48,6 +50,16 @@ func (s *CertificateService) SetTargetRepo(repo repository.TargetRepository) {
|
||||
s.targetRepo = repo
|
||||
}
|
||||
|
||||
// SetJobRepo sets the job repository for creating renewal/issuance jobs.
|
||||
func (s *CertificateService) SetJobRepo(repo repository.JobRepository) {
|
||||
s.jobRepo = repo
|
||||
}
|
||||
|
||||
// SetKeygenMode sets the key generation mode (agent or server).
|
||||
func (s *CertificateService) SetKeygenMode(mode string) {
|
||||
s.keygenMode = mode
|
||||
}
|
||||
|
||||
// List returns a paginated list of certificates matching the filter.
|
||||
func (s *CertificateService) List(ctx context.Context, filter *repository.CertificateFilter) ([]*domain.ManagedCertificate, int, error) {
|
||||
certs, total, err := s.certRepo.List(ctx, filter)
|
||||
@@ -195,6 +207,8 @@ func (s *CertificateService) GetVersions(ctx context.Context, certID string) ([]
|
||||
}
|
||||
|
||||
// TriggerRenewalWithActor initiates a renewal job if the certificate is eligible.
|
||||
// Creates a Renewal job (or Issuance for new certs) so the scheduler's job processor
|
||||
// can pick it up and route it through the issuer connector.
|
||||
func (s *CertificateService) TriggerRenewalWithActor(ctx context.Context, certID string, actor string) error {
|
||||
cert, err := s.certRepo.Get(ctx, certID)
|
||||
if err != nil {
|
||||
@@ -220,6 +234,45 @@ func (s *CertificateService) TriggerRenewalWithActor(ctx context.Context, certID
|
||||
return fmt.Errorf("failed to update certificate status: %w", err)
|
||||
}
|
||||
|
||||
// Create a renewal job so the job processor can pick it up.
|
||||
// In agent keygen mode, the job starts as AwaitingCSR so the agent
|
||||
// generates the key pair and submits a CSR. In server mode, it starts as Pending.
|
||||
if s.jobRepo != nil {
|
||||
jobStatus := domain.JobStatusPending
|
||||
if s.keygenMode == "agent" {
|
||||
jobStatus = domain.JobStatusAwaitingCSR
|
||||
}
|
||||
|
||||
// Determine job type: Issuance for certs that have never been issued,
|
||||
// Renewal for certs that already have a version.
|
||||
jobType := domain.JobTypeRenewal
|
||||
if cert.ExpiresAt.IsZero() || cert.ExpiresAt.Year() < 2000 {
|
||||
jobType = domain.JobTypeIssuance
|
||||
}
|
||||
|
||||
job := &domain.Job{
|
||||
ID: generateID("job"),
|
||||
CertificateID: cert.ID,
|
||||
Type: jobType,
|
||||
Status: jobStatus,
|
||||
MaxAttempts: 3,
|
||||
ScheduledAt: time.Now(),
|
||||
CreatedAt: time.Now(),
|
||||
}
|
||||
|
||||
if err := s.jobRepo.Create(ctx, job); err != nil {
|
||||
slog.Error("failed to create renewal job", "cert_id", cert.ID, "error", err)
|
||||
return fmt.Errorf("failed to create renewal job: %w", err)
|
||||
}
|
||||
|
||||
slog.Info("created renewal job via API trigger",
|
||||
"job_id", job.ID,
|
||||
"cert_id", cert.ID,
|
||||
"job_type", string(jobType),
|
||||
"job_status", string(jobStatus),
|
||||
"keygen_mode", s.keygenMode)
|
||||
}
|
||||
|
||||
// Record audit event
|
||||
if err := s.auditService.RecordEvent(ctx, actor, domain.ActorTypeUser,
|
||||
"renewal_triggered", "certificate", certID,
|
||||
|
||||
Reference in New Issue
Block a user