Files
certctl/internal/api/handler/bulk_partial_failure_test.go
T
Shankar 345bafe5aa Bundle C: Renewal/reliability cluster — 7 findings closed
Closes M-006 + M-007 + M-008 + M-015 + M-016 + M-019 + M-020 from
comprehensive-audit-2026-04-25. M-028 was already closed by the
Bundle B CI follow-up.

M-006 (CWE-913) — Idempotent migration 000014
  migrations/000014_policy_violation_severity_check.up.sql:
    Prepended ALTER TABLE ... DROP CONSTRAINT IF EXISTS before the
    ADD. Mirrors the down migration's existing IF EXISTS shape and
    the M-7 idempotent-index idiom. Re-runs against partially-applied
    DBs now succeed.

M-007 — Bulk-op partial-failure tests (3 new)
  internal/api/handler/bulk_partial_failure_test.go:
    TestBulkRevoke_PartialFailure_ReportsBoth
    TestBulkRenew_PartialFailure_ReportsBoth
    TestBulkReassign_PartialFailure_ReportsBoth
  Each asserts HTTP 200 + both success/failure counters round-trip
  + per-cert errors[] preserved with non-empty messages so operators
  can correlate each failure to its certificate ID.

M-008 — Admin-gated handler enumeration pin (verified-already-clean)
  Recon: only one admin-gated handler — bulk_revocation.go — with
  full 3-branch test triplet already in place. health.go calls
  IsAdmin informationally to surface the flag to the GUI without
  gating.
  internal/api/handler/m008_admin_gate_test.go:
    Walks every handler .go file, asserts every middleware.IsAdmin
    call site is in AdminGatedHandlers (with required test triplet)
    or InformationalIsAdminCallers (justified). Adding a new admin
    gate without updating both the constant AND adding the test
    triplet fails CI.

M-015 — Single-profile cardinality pin (verified-already-clean)
  Audit claim 'no cardinality validation' was wrong — enforced at
  struct level. domain.ManagedCertificate.{CertificateProfileID,
  RenewalPolicyID,IssuerID,OwnerID} and RenewalPolicy.
  CertificateProfileID are bare strings, not slices.
  internal/domain/m015_cardinality_test.go:
    reflect-based pin on kind=String. Schema change to N:N would
    have to update renewal.go's lookup loop in the same commit.

M-016 (CWE-754) — Reap stale-agent jobs
  internal/repository/postgres/job.go::ListJobsWithOfflineAgents:
    JOIN jobs to agents on agent_id, filter (status=Running AND
    a.last_heartbeat_at < cutoff), exclude server-keygen jobs.
  internal/service/job.go::ReapJobsWithOfflineAgents:
    Flips matched jobs to Failed reason agent_offline so I-001
    retry loop re-queues them on a healthy agent. Records audit
    event per reap.
  internal/scheduler/scheduler.go:
    Scheduler.runJobTimeout cycle now calls both reaper arms.
    agentOfflineJobTTL default 5min (5x agent-health-check default);
    SetAgentOfflineJobTTL knob for operator override.
  internal/service/job_offline_agent_reaper_test.go: 6 unit tests
  cover happy path, server-keygen-skip, non-Running-skip, non-
  positive-TTL fail-loud, repo-error propagation, audit-event
  recording.

M-019 — Configurable ARI HTTP timeout
  Audit claim 'no fallback timeout' was wrong — ari.go:52 already
  had a 15s timeout. Bundle C makes it configurable.
  internal/connector/issuer/acme/acme.go:
    Config.ARIHTTPTimeoutSeconds field with env path
    CERTCTL_ACME_ARI_HTTP_TIMEOUT_SECONDS.
  internal/connector/issuer/acme/ari.go:
    Both HTTP clients (GetRenewalInfo + getARIEndpoint) now use the
    new ariHTTPTimeout() helper. Zero / negative / nil-config all
    fall back to the historic 15s default.
  ari_timeout_test.go: 4 dispatch arm tests.

M-020 (CWE-770) — OCSP DoS hardening
  Pre-bundle the noAuthHandler chain had no rate limit. An attacker
  could DoS the OCSP responder, which for fail-open relying parties
  is a revocation bypass.
  cmd/server/main.go:
    noAuthHandler refactored from fixed middleware.Chain(...) to a
    conditional slice that appends middleware.NewRateLimiter when
    cfg.RateLimit.Enabled. Per-IP keying applies; OCSP/CRL/EST/SCEP
    are unauth.
  docs/security.md (NEW):
    Operator runbook documenting Must-Staple TLS Feature extension
    RFC 7633 as the architectural fix for fail-open relying parties.
    Profile-flip guidance + nginx/Apache/HAProxy/Envoy stapling
    snippets + explicit scope statement on what the rate limiter
    alone does NOT solve.

Audit deliverables:
  cowork/comprehensive-audit-2026-04-25/audit-report.md: score
    31/55 -> 38/55 closed (Medium 13/27 -> 20/27).
  cowork/comprehensive-audit-2026-04-25/findings.yaml: 7 status
    flips open -> closed with closure notes citing the Bundle C
    mechanism.
  certctl/CHANGELOG.md: Bundle C section under [unreleased].

Verification:
  go vet ./internal/service ./internal/scheduler ./internal/connector/issuer/acme
    ./internal/api/handler ./internal/domain ./cmd/server     clean
  go test -count=1 -short on the same packages              all green
  helm template + helm lint                                 clean
  internal/repository/postgres setup-fail                   sandbox disk
    pressure (same on master HEAD before this branch)
2026-04-27 00:08:25 +00:00

181 lines
6.4 KiB
Go

package handler
import (
"bytes"
"context"
"encoding/json"
"net/http"
"net/http/httptest"
"testing"
"github.com/shankar0123/certctl/internal/domain"
)
// Bundle C / Audit M-007 (CWE-754): partial-failure tests for the three
// bulk endpoints. Pre-bundle all three handlers had only happy-path
// (TotalRevoked = TotalMatched, no Errors) and full-failure (service
// returns err) tests. The mixed-result branch — where some certs
// succeed and others fail — is the most operationally common shape
// and was completely uncovered.
//
// Each test asserts:
// 1. HTTP 200 (mixed result is a successful HTTP response carrying
// both succeeded and failed counters).
// 2. The response body's TotalMatched / Total<verb> / TotalFailed
// counters all round-trip from the service mock.
// 3. The Errors[] array is preserved and operators can correlate
// each failure to its certificate ID.
// --- bulk-revoke ----------------------------------------------------------
func TestBulkRevoke_PartialFailure_ReportsBoth(t *testing.T) {
svc := &mockBulkRevocationService{
BulkRevokeFn: func(ctx context.Context, criteria domain.BulkRevocationCriteria, reason string, actor string) (*domain.BulkRevocationResult, error) {
return &domain.BulkRevocationResult{
TotalMatched: 3,
TotalRevoked: 2,
TotalSkipped: 0,
TotalFailed: 1,
Errors: []domain.BulkRevocationError{
{CertificateID: "mc-failed", Error: "issuer connector unreachable"},
},
}, nil
},
}
h := NewBulkRevocationHandler(svc)
body := `{"reason":"keyCompromise","certificate_ids":["mc-1","mc-2","mc-failed"]}`
req := httptest.NewRequest(http.MethodPost, "/api/v1/certificates/bulk-revoke", bytes.NewBufferString(body))
req.Header.Set("Content-Type", "application/json")
req = req.WithContext(adminContext())
w := httptest.NewRecorder()
h.BulkRevoke(w, req)
if w.Code != http.StatusOK {
t.Fatalf("partial failure must still return HTTP 200, got %d", w.Code)
}
var result domain.BulkRevocationResult
if err := json.NewDecoder(w.Body).Decode(&result); err != nil {
t.Fatalf("decode response: %v", err)
}
if result.TotalMatched != 3 {
t.Errorf("TotalMatched = %d, want 3", result.TotalMatched)
}
if result.TotalRevoked != 2 {
t.Errorf("TotalRevoked = %d, want 2", result.TotalRevoked)
}
if result.TotalFailed != 1 {
t.Errorf("TotalFailed = %d, want 1", result.TotalFailed)
}
if len(result.Errors) != 1 {
t.Fatalf("Errors len = %d, want 1", len(result.Errors))
}
if result.Errors[0].CertificateID != "mc-failed" {
t.Errorf("error CertificateID = %q, want mc-failed", result.Errors[0].CertificateID)
}
if result.Errors[0].Error == "" {
t.Error("error message must be non-empty so operators can triage")
}
}
// --- bulk-renew -----------------------------------------------------------
func TestBulkRenew_PartialFailure_ReportsBoth(t *testing.T) {
svc := &mockBulkRenewalService{
BulkRenewFn: func(ctx context.Context, criteria domain.BulkRenewalCriteria, actor string) (*domain.BulkRenewalResult, error) {
return &domain.BulkRenewalResult{
TotalMatched: 3,
TotalEnqueued: 2,
TotalSkipped: 0,
TotalFailed: 1,
Errors: []domain.BulkOperationError{
{CertificateID: "mc-failed", Error: "renewal job enqueue failed: db timeout"},
},
}, nil
},
}
h := NewBulkRenewalHandler(svc)
body := `{"certificate_ids":["mc-1","mc-2","mc-failed"]}`
req := httptest.NewRequest(http.MethodPost, "/api/v1/certificates/bulk-renew", bytes.NewBufferString(body))
req.Header.Set("Content-Type", "application/json")
req = req.WithContext(authenticatedContext("test-actor"))
w := httptest.NewRecorder()
h.BulkRenew(w, req)
if w.Code != http.StatusOK {
t.Fatalf("partial failure must still return HTTP 200, got %d", w.Code)
}
var result domain.BulkRenewalResult
if err := json.NewDecoder(w.Body).Decode(&result); err != nil {
t.Fatalf("decode response: %v", err)
}
if result.TotalMatched != 3 || result.TotalEnqueued != 2 || result.TotalFailed != 1 {
t.Errorf("counters mismatch: matched=%d enqueued=%d failed=%d, want 3/2/1",
result.TotalMatched, result.TotalEnqueued, result.TotalFailed)
}
if len(result.Errors) != 1 || result.Errors[0].CertificateID != "mc-failed" {
t.Errorf("Errors not preserved: %+v", result.Errors)
}
}
// --- bulk-reassign --------------------------------------------------------
func TestBulkReassign_PartialFailure_ReportsBoth(t *testing.T) {
svc := &mockBulkReassignmentService{
BulkReassignFn: func(ctx context.Context, request domain.BulkReassignmentRequest, actor string) (*domain.BulkReassignmentResult, error) {
return &domain.BulkReassignmentResult{
TotalMatched: 3,
TotalReassigned: 2,
TotalSkipped: 0,
TotalFailed: 1,
Errors: []domain.BulkOperationError{
{CertificateID: "mc-failed", Error: "FK violation: cert no longer exists"},
},
}, nil
},
}
h := NewBulkReassignmentHandler(svc)
body := `{"certificate_ids":["mc-1","mc-2","mc-failed"],"owner_id":"o-bob"}`
req := httptest.NewRequest(http.MethodPost, "/api/v1/certificates/bulk-reassign", bytes.NewBufferString(body))
req.Header.Set("Content-Type", "application/json")
req = req.WithContext(authenticatedContext("test-actor"))
w := httptest.NewRecorder()
h.BulkReassign(w, req)
if w.Code != http.StatusOK {
t.Fatalf("partial failure must still return HTTP 200, got %d", w.Code)
}
var result domain.BulkReassignmentResult
if err := json.NewDecoder(w.Body).Decode(&result); err != nil {
t.Fatalf("decode response: %v", err)
}
if result.TotalMatched != 3 || result.TotalReassigned != 2 || result.TotalFailed != 1 {
t.Errorf("counters mismatch: matched=%d reassigned=%d failed=%d, want 3/2/1",
result.TotalMatched, result.TotalReassigned, result.TotalFailed)
}
if len(result.Errors) != 1 || result.Errors[0].CertificateID != "mc-failed" {
t.Errorf("Errors not preserved: %+v", result.Errors)
}
}
// --- helper context for unauth-allowed handlers (renew + reassign aren't admin-gated) ---
func authenticatedContext(actor string) context.Context {
type userKey struct{}
// The middleware UserKey is a private type in the middleware package, so
// in this handler test we can't construct one directly. Bulk-renew and
// bulk-reassign read the actor through the same middleware.GetUser path
// that bulk-revoke does — adminContext() in the existing test suite is
// the canonical helper. Reuse it (delivers both UserKey and AdminKey).
_ = userKey{}
return adminContext()
}