Files
logarchiver/internal/vaultgpg/client.go
T
benvin c05ccfcb5d
ci/woodpecker/pr/build Pipeline was successful
ci/woodpecker/pr/pre-commit Pipeline was successful
ci/woodpecker/pr/test Pipeline was successful
Initial implementation: NATS->S3 archiver + search/retrieve CLI
logarchiver replaces the plain Vector archiver leg of the centralized
logging stack (argocd-apps #296) with a Go service that archives raw logs
from NATS JetStream to S3 as zstd-compressed, OpenPGP-encrypted, indexed
objects, plus an operator CLI to search the index and retrieve/decrypt
archived logs. It adds the things that outgrew Vector: zstd compression,
encryption keyed from Ben's Vault GPG secrets engine, a searchable
ClickHouse index, and sink-conditional acks (a batch is acknowledged to
JetStream only after the object is durably in S3 AND indexed).

Service (`logarchiver run`):
- Durable JetStream pull consumer (stream LOGS, durable archiver, subject
  filter default logs.k8s.vault.>), explicit acks, independent offsets.
- Batch per subject by size/count/time -> NDJSON -> zstd -> encrypt -> S3
  PUT -> ClickHouse index row -> ack. On any failure the batch is Nak'd and
  redelivered, so nothing is lost on a sink outage.
- Encryption is a wrapped-DEK envelope (container LARC1): the bulk is
  AES-256-GCM framed under a random data key, and only that 32-byte key is
  OpenPGP-encrypted to the engine's public key. This is because the Vault
  GPG engine does whole-payload decrypt only; retrieval round-trips just the
  tiny wrapped key regardless of object size. Public key fetched from the
  engine or a mounted file (configurable); key fingerprint recorded per
  object; periodic pubkey refresh for rotation.
- Prometheus metrics, structured slog, graceful drain on shutdown.

CLI:
- `search` queries the index (subject/host/time) and lists matching objects.
- `fetch` downloads, decrypts via the Vault GPG engine, unzstds and emits
  NDJSON (optionally re-filtered by host/time).
- `init-schema` creates/prints the ClickHouse archive_index DDL.
- cobra `completion` subcommands.

Config via file+env (k8s-friendly, secrets from env), boundaries (NATS/S3/
ClickHouse/Vault) behind interfaces with unit tests (config, batching,
host/subject extraction, crypto roundtrip with a test key, ack-after-persist
with fakes, search query building). go build/vet/test -race clean;
golangci-lint v2 clean. Woodpecker CI: build/test/pre-commit on PR; on v*
tag a container image plus a Gitea binary release + rpm-internal RPM. Docs
per subcommand + architecture + retrieval runbook + deployment drop-in.

Claude-Session: https://claude.ai/code/session_015ur3i7D2azsMAWTSVABApv
2026-07-27 23:22:40 +10:00

196 lines
5.6 KiB
Go

// Package vaultgpg is a thin client for Ben's Vault GPG secrets engine
// (vault-plugin-secrets-gpg), used two ways:
//
// - the service reads the ARMORED PUBLIC key (GET <mount>/keys/<name>) to
// encrypt objects locally; and
// - the CLI decrypts a wrapped DEK (POST <mount>/decrypt/<name>) to retrieve
// objects. The engine does whole-payload decrypt only, but logarchiver only
// ever sends it the tiny wrapped-DEK blob, so that is a non-issue.
//
// Auth mirrors passv: ambient VAULT_* env (token or ~/.vault-token) for humans,
// or the kubernetes auth method for the in-cluster service.
package vaultgpg
import (
"context"
"encoding/base64"
"fmt"
"os"
"path/filepath"
"strings"
"time"
vault "github.com/hashicorp/vault/api"
)
// Config configures the Vault client.
type Config struct {
Address string
Mount string // e.g. "gpg"
AuthMethod string // "token" | "kubernetes"
K8sRole string
K8sMount string // e.g. "k8s/au/syd1"
K8sJWTPath string
CAFile string
}
// Client wraps the Vault API client for GPG-engine operations.
type Client struct {
api *vault.Client
mount string
}
// New builds a Client and authenticates per cfg.AuthMethod.
func New(ctx context.Context, cfg Config) (*Client, error) {
vc := vault.DefaultConfig()
if err := vc.ReadEnvironment(); err != nil {
return nil, fmt.Errorf("read vault env: %w", err)
}
if cfg.Address != "" {
vc.Address = cfg.Address
}
if cfg.CAFile != "" {
if err := vc.ConfigureTLS(&vault.TLSConfig{CACert: cfg.CAFile}); err != nil {
return nil, fmt.Errorf("configure vault tls: %w", err)
}
}
api, err := vault.NewClient(vc)
if err != nil {
return nil, fmt.Errorf("new vault client: %w", err)
}
mount := cfg.Mount
if mount == "" {
mount = "gpg"
}
c := &Client{api: api, mount: strings.Trim(mount, "/")}
switch cfg.AuthMethod {
case "", "token":
if api.Token() == "" {
tok, err := resolveToken()
if err != nil {
return nil, err
}
api.SetToken(tok)
}
case "kubernetes":
if err := c.k8sLogin(ctx, cfg); err != nil {
return nil, err
}
default:
return nil, fmt.Errorf("unknown vault auth_method %q", cfg.AuthMethod)
}
return c, nil
}
func (c *Client) k8sLogin(ctx context.Context, cfg Config) error {
jwtPath := cfg.K8sJWTPath
if jwtPath == "" {
jwtPath = "/var/run/secrets/kubernetes.io/serviceaccount/token"
}
jwt, err := os.ReadFile(jwtPath)
if err != nil {
return fmt.Errorf("read service account token: %w", err)
}
mount := cfg.K8sMount
if mount == "" {
mount = "kubernetes"
}
path := fmt.Sprintf("auth/%s/login", strings.Trim(mount, "/"))
secret, err := c.api.Logical().WriteWithContext(ctx, path, map[string]any{
"role": cfg.K8sRole,
"jwt": strings.TrimSpace(string(jwt)),
})
if err != nil {
return fmt.Errorf("kubernetes login: %w", err)
}
if secret == nil || secret.Auth == nil || secret.Auth.ClientToken == "" {
return fmt.Errorf("kubernetes login returned no token")
}
c.api.SetToken(secret.Auth.ClientToken)
return nil
}
// resolveToken mirrors passv: VAULT_TOKEN, else ~/.vault-token.
func resolveToken() (string, error) {
if t := os.Getenv("VAULT_TOKEN"); t != "" {
return t, nil
}
home, err := os.UserHomeDir()
if err != nil {
return "", fmt.Errorf("no VAULT_TOKEN and cannot find home dir: %w", err)
}
data, err := os.ReadFile(filepath.Join(home, ".vault-token"))
if err != nil {
return "", fmt.Errorf("no VAULT_TOKEN and no ~/.vault-token: %w", err)
}
tok := strings.TrimSpace(string(data))
if tok == "" {
return "", fmt.Errorf("~/.vault-token is empty")
}
return tok, nil
}
// PublicKey is the result of reading a GPG engine key.
type PublicKey struct {
Armored string
Fingerprint string
}
// FetchPublicKey reads <mount>/keys/<name> and returns the latest armored public
// key and its fingerprint.
func (c *Client) FetchPublicKey(ctx context.Context, name string) (PublicKey, error) {
path := fmt.Sprintf("%s/keys/%s", c.mount, name)
secret, err := c.api.Logical().ReadWithContext(ctx, path)
if err != nil {
return PublicKey{}, fmt.Errorf("read %s: %w", path, err)
}
if secret == nil || secret.Data == nil {
return PublicKey{}, fmt.Errorf("key %q not found at %s", name, path)
}
pub, _ := secret.Data["public_key"].(string)
if pub == "" {
return PublicKey{}, fmt.Errorf("key %q has no public_key field", name)
}
fpr, _ := secret.Data["fingerprint"].(string)
return PublicKey{Armored: pub, Fingerprint: fpr}, nil
}
// Decrypt sends ciphertext (raw binary OpenPGP) to <mount>/decrypt/<name> and
// returns the plaintext. The engine auto-detects binary vs armored; we send
// base64 of the raw bytes, as passv does.
func (c *Client) Decrypt(ctx context.Context, name string, ciphertext []byte) ([]byte, error) {
path := fmt.Sprintf("%s/decrypt/%s", c.mount, name)
secret, err := c.api.Logical().WriteWithContext(ctx, path, map[string]any{
"ciphertext": base64.StdEncoding.EncodeToString(ciphertext),
})
if err != nil {
return nil, fmt.Errorf("decrypt via %s: %w", path, err)
}
if secret == nil || secret.Data == nil {
return nil, fmt.Errorf("decrypt returned no data")
}
b64, _ := secret.Data["plaintext"].(string)
if b64 == "" {
return nil, fmt.Errorf("decrypt returned no plaintext")
}
plain, err := base64.StdEncoding.DecodeString(b64)
if err != nil {
return nil, fmt.Errorf("decode plaintext: %w", err)
}
return plain, nil
}
// TokenTTL returns the remaining lease TTL of the current token, for diagnostics.
func (c *Client) TokenTTL(ctx context.Context) (time.Duration, error) {
secret, err := c.api.Auth().Token().LookupSelfWithContext(ctx)
if err != nil {
return 0, err
}
ttl, err := secret.TokenTTL()
if err != nil {
return 0, err
}
return ttl, nil
}