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:
shankar0123
2026-04-02 17:02:20 -04:00
parent 2238f28610
commit b059ec930f
19 changed files with 2102 additions and 84 deletions
+42 -13
View File
@@ -636,23 +636,50 @@ func (s *RenewalService) CompleteAgentCSRRenewal(ctx context.Context, job *domai
}
// createDeploymentJobs creates pending deployment jobs for each target associated with a cert.
// If cert.TargetIDs is empty (common — the repository doesn't populate this field),
// falls back to querying certificate_target_mappings via targetRepo.ListByCertificate.
func (s *RenewalService) createDeploymentJobs(ctx context.Context, cert *domain.ManagedCertificate) {
if len(cert.TargetIDs) == 0 {
// Resolve targets: prefer in-memory TargetIDs, fall back to DB query
type targetInfo struct {
id string
agentID string
}
var targets []targetInfo
if len(cert.TargetIDs) > 0 {
// TargetIDs populated (e.g. from test or manual wiring)
for _, tid := range cert.TargetIDs {
ti := targetInfo{id: tid}
if s.targetRepo != nil {
if target, err := s.targetRepo.Get(ctx, tid); err == nil && target.AgentID != "" {
ti.agentID = target.AgentID
}
}
targets = append(targets, ti)
}
} else if s.targetRepo != nil {
// TargetIDs empty — query certificate_target_mappings via repository
dbTargets, err := s.targetRepo.ListByCertificate(ctx, cert.ID)
if err != nil {
slog.Error("failed to query targets for certificate", "cert_id", cert.ID, "error", err)
return
}
for _, t := range dbTargets {
targets = append(targets, targetInfo{id: t.ID, agentID: t.AgentID})
}
}
if len(targets) == 0 {
slog.Debug("no targets found for certificate, skipping deployment", "cert_id", cert.ID)
return
}
for _, targetID := range cert.TargetIDs {
tid := targetID
// Resolve agent_id from target for job routing
for _, t := range targets {
tid := t.id
var agentIDPtr *string
if s.targetRepo != nil {
target, err := s.targetRepo.Get(ctx, tid)
if err != nil {
slog.Warn("failed to resolve agent for deployment job", "target_id", tid, "error", err)
} else if target.AgentID != "" {
agentID := target.AgentID
agentIDPtr = &agentID
}
if t.agentID != "" {
aid := t.agentID
agentIDPtr = &aid
}
deployJob := &domain.Job{
@@ -667,7 +694,9 @@ func (s *RenewalService) createDeploymentJobs(ctx context.Context, cert *domain.
CreatedAt: time.Now(),
}
if err := s.jobRepo.Create(ctx, deployJob); err != nil {
slog.Error("failed to create deployment job for target", "target_id", targetID, "error", err)
slog.Error("failed to create deployment job for target", "target_id", tid, "cert_id", cert.ID, "error", err)
} else {
slog.Info("created deployment job", "job_id", deployJob.ID, "cert_id", cert.ID, "target_id", tid, "agent_id", t.agentID)
}
}
}