Fix audit findings: lock architecture, security, deployment hardening

Close all 14 findings from the codebase audit (1 high, 5 medium, 8 low):

- Locking: replace the global API and workspace mutexes with per-instance
  and per-user keyed locks (new internal/api/locks.go) so a slow restore,
  upgrade or transfer no longer blocks unrelated users or instances; move
  Docker I/O out of the build queue and invalidate concurrent image-index
  observations with a generation counter; serialize instance deletion
  behind in-flight creation.
- Security: equalize login timing for unknown usernames, periodically
  purge expired sessions/refresh tokens/lock rows, URL-encode orphan IDs
  in the frontend, upgrade vitest 3.x->5.x to clear 3 npm audit
  vulnerabilities (2 critical RCE).
- Deployment: add a -healthcheck mode probing /healthz (used by Dockerfile
  HEALTHCHECK and compose), make ADMIN_PASSWORD optional in compose with
  removal guidance after first start, exclude test scripts from the image,
  and cap panel resources (cpus: 2, pids_limit: 512).
- Reliability: check rows.Err() on admin listing loops, surface intent
  polling errors without sticking, disable close during in-flight create.

Verified: go build/vet, full go test -race -count=1 ./..., frontend
tsc build + 32 tests, npm audit 0, compose config, real-container
healthcheck.
This commit is contained in:
2026-10-13 20:59:28 +08:00
parent 85332bbc56
commit 66abb76318
33 changed files with 1065 additions and 540 deletions
+30
View File
@@ -7,7 +7,9 @@ import (
"git.misaka.ren/m1saka/dsh-web/internal/api"
"git.misaka.ren/m1saka/dsh-web/internal/store"
"golang.org/x/crypto/bcrypt"
"io"
"log"
"net"
"net/http"
"os"
"os/signal"
@@ -18,10 +20,37 @@ import (
)
func main() {
if len(os.Args) > 1 && os.Args[1] == "-healthcheck" {
if err := healthcheck(); err != nil {
log.Printf("healthcheck failed: %v", err)
os.Exit(1)
}
return
}
if err := run(); err != nil {
log.Fatal(err)
}
}
// healthcheck probes the local /healthz endpoint for container health
// reporting; it avoids shipping curl into the runtime image.
func healthcheck() error {
addr := getenv("LISTEN_ADDR", "127.0.0.1:8088")
if host, port, err := net.SplitHostPort(addr); err == nil && (host == "" || host == "0.0.0.0" || host == "::") {
addr = net.JoinHostPort("127.0.0.1", port)
}
client := &http.Client{Timeout: 5 * time.Second}
resp, err := client.Get("http://" + addr + "/healthz")
if err != nil {
return err
}
defer resp.Body.Close()
_, _ = io.Copy(io.Discard, io.LimitReader(resp.Body, 4096))
if resp.StatusCode != http.StatusOK {
return fmt.Errorf("healthz returned %d", resp.StatusCode)
}
return nil
}
func run() error {
if err := api.ValidateAuthConfig(); err != nil {
return err
@@ -100,6 +129,7 @@ func run() error {
return fmt.Errorf("creation intent recovery: %w", err)
}
go panel.RunQuotaMonitor(ctx)
go panel.RunSessionCleanup(ctx)
return serve(ctx, srv)
}
+29
View File
@@ -5,6 +5,7 @@ import (
"io"
"net"
"net/http"
"net/http/httptest"
"os"
"path/filepath"
"strings"
@@ -86,3 +87,31 @@ func TestServeWaitsForActiveHandler(t *testing.T) {
t.Fatal(err)
}
}
func TestHealthcheckProbesLocalEndpoint(t *testing.T) {
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
if r.URL.Path != "/healthz" {
http.NotFound(w, r)
return
}
w.Write([]byte("ok"))
}))
defer srv.Close()
_, port, err := net.SplitHostPort(srv.Listener.Addr().String())
if err != nil {
t.Fatal(err)
}
t.Setenv("LISTEN_ADDR", "127.0.0.1:"+port)
if err := healthcheck(); err != nil {
t.Fatalf("healthy server rejected: %v", err)
}
// The container listens on 0.0.0.0; the probe must target loopback.
t.Setenv("LISTEN_ADDR", "0.0.0.0:"+port)
if err := healthcheck(); err != nil {
t.Fatalf("wildcard address rejected: %v", err)
}
t.Setenv("LISTEN_ADDR", "127.0.0.1:1")
if err := healthcheck(); err == nil {
t.Fatal("dead endpoint accepted")
}
}