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
@@ -1,6 +1,7 @@
package api
import (
"context"
"crypto/hmac"
"crypto/rand"
"crypto/sha256"
@@ -9,6 +10,7 @@ import (
"encoding/hex"
"encoding/json"
"errors"
"log"
"net/http"
"net/url"
"os"
@@ -191,6 +193,34 @@ func (a *API) accountLocked(username string) (bool, error) {
}
return until > time.Now().Unix(), err
}
// RunSessionCleanup removes expired sessions, their refresh tokens and elapsed
// login locks every ten minutes; without it the sessions table grows without
// bound because SessionUser only filters rows on read.
func (a *API) RunSessionCleanup(ctx context.Context) {
ticker := time.NewTicker(10 * time.Minute)
defer ticker.Stop()
for {
a.cleanupSessions(time.Now().Unix())
select {
case <-ctx.Done():
return
case <-ticker.C:
}
}
}
func (a *API) cleanupSessions(now int64) {
for _, q := range []struct{ name, sql string }{
{"refresh tokens", "DELETE FROM auth_refresh WHERE sid IN (SELECT id FROM sessions WHERE expires<=?)"},
{"sessions", "DELETE FROM sessions WHERE expires<=?"},
{"login locks", "DELETE FROM auth_failures WHERE locked_until>0 AND locked_until<=?"},
} {
if _, err := a.s.DB.Exec(q.sql, now); err != nil {
log.Printf("session cleanup (%s): %v", q.name, err)
}
}
}
func (a *API) failedLogin(username string) error {
_, err := a.s.DB.Exec(`INSERT INTO auth_failures(username,failures,locked_until) VALUES(?,1,0)
ON CONFLICT(username) DO UPDATE SET