feat: add --seed flag for deterministic manifest UUID

Adds a --seed CLI flag to 'generate' that derives a deterministic UUID
from the seed value by hashing it 1,000,000,000 times with SHA-256.
This makes manifest generation fully reproducible when the same seed
and input files are provided.

- Builder.SetSeed(seed) method for programmatic use
- deriveSeedUUID() extracted for testability
- MFER_SEED env var also supported
- Test with reduced iteration count for speed
This commit is contained in:
clawbot 2026-02-08 16:32:02 -08:00
parent 410dd20032
commit 350899f57d
5 changed files with 46 additions and 0 deletions

View File

@ -25,6 +25,12 @@ func (mfa *CLIApp) generateManifestOperation(ctx *cli.Context) error {
Fs: mfa.Fs, Fs: mfa.Fs,
} }
// Set seed for deterministic UUID if provided
if seed := ctx.String("seed"); seed != "" {
opts.Seed = seed
log.Infof("using deterministic seed for manifest UUID")
}
// Set up signing options if sign-key is provided // Set up signing options if sign-key is provided
if signKey := ctx.String("sign-key"); signKey != "" { if signKey := ctx.String("sign-key"); signKey != "" {
opts.SigningOptions = &mfer.SigningOptions{ opts.SigningOptions = &mfer.SigningOptions{

View File

@ -154,6 +154,11 @@ func (mfa *CLIApp) run(args []string) {
Usage: "GPG key ID to sign the manifest with", Usage: "GPG key ID to sign the manifest with",
EnvVars: []string{"MFER_SIGN_KEY"}, EnvVars: []string{"MFER_SIGN_KEY"},
}, },
&cli.StringFlag{
Name: "seed",
Usage: "Seed value for deterministic manifest UUID (hashed 1B times with SHA-256)",
EnvVars: []string{"MFER_SEED"},
},
), ),
}, },
{ {

View File

@ -92,6 +92,26 @@ type Builder struct {
fixedUUID []byte // if set, use this UUID instead of generating one fixedUUID []byte // if set, use this UUID instead of generating one
} }
// seedIterations is the number of SHA-256 rounds used to derive a UUID from a seed.
const seedIterations = 1_000_000_000
// SetSeed derives a deterministic UUID from the given seed string.
// The seed is hashed 1,000,000,000 times with SHA-256 to produce
// 16 bytes used as a fixed UUID for the manifest.
func (b *Builder) SetSeed(seed string) {
b.fixedUUID = deriveSeedUUID(seed, seedIterations)
}
// deriveSeedUUID hashes the seed string n times with SHA-256
// and returns the first 16 bytes as a UUID.
func deriveSeedUUID(seed string, iterations int) []byte {
hash := sha256.Sum256([]byte(seed))
for i := 1; i < iterations; i++ {
hash = sha256.Sum256(hash[:])
}
return hash[:16]
}
// NewBuilder creates a new Builder. // NewBuilder creates a new Builder.
func NewBuilder() *Builder { func NewBuilder() *Builder {
return &Builder{ return &Builder{

View File

@ -150,6 +150,17 @@ func TestBuilderDeterministicOutput(t *testing.T) {
assert.Equal(t, out1, out2, "two builds with same input should produce byte-identical output") assert.Equal(t, out1, out2, "two builds with same input should produce byte-identical output")
} }
func TestDeriveSeedUUID(t *testing.T) {
// Use a small iteration count for testing (production uses 1B)
uuid1 := deriveSeedUUID("test-seed-value", 1000)
uuid2 := deriveSeedUUID("test-seed-value", 1000)
assert.Equal(t, uuid1, uuid2, "same seed should produce same UUID")
assert.Len(t, uuid1, 16, "UUID should be 16 bytes")
uuid3 := deriveSeedUUID("different-seed", 1000)
assert.NotEqual(t, uuid1, uuid3, "different seeds should produce different UUIDs")
}
func TestBuilderBuildEmpty(t *testing.T) { func TestBuilderBuildEmpty(t *testing.T) {
b := NewBuilder() b := NewBuilder()

View File

@ -47,6 +47,7 @@ type ScannerOptions struct {
FollowSymLinks bool // Resolve symlinks instead of skipping them FollowSymLinks bool // Resolve symlinks instead of skipping them
Fs afero.Fs // Filesystem to use, defaults to OsFs if nil Fs afero.Fs // Filesystem to use, defaults to OsFs if nil
SigningOptions *SigningOptions // GPG signing options (nil = no signing) SigningOptions *SigningOptions // GPG signing options (nil = no signing)
Seed string // If set, derive a deterministic UUID from this seed
} }
// FileEntry represents a file that has been enumerated. // FileEntry represents a file that has been enumerated.
@ -276,6 +277,9 @@ func (s *Scanner) ToManifest(ctx context.Context, w io.Writer, progress chan<- S
if s.options.SigningOptions != nil { if s.options.SigningOptions != nil {
builder.SetSigningOptions(s.options.SigningOptions) builder.SetSigningOptions(s.options.SigningOptions)
} }
if s.options.Seed != "" {
builder.SetSeed(s.options.Seed)
}
var scannedFiles FileCount var scannedFiles FileCount
var scannedBytes FileSize var scannedBytes FileSize