eric/narratio
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 15 Wiki Activity

Implemented shared S3 audio caching for prepare and restore --include-audio

Browse Source
This commit is contained in:
Eric Rakestraw
2026-05-21 22:22:08 -05:00
parent 3022f20beb
commit b817a5b772
24 changed files with 876 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
internal/app/commands_test.go
View File

@@ -410,6 +410,10 @@ func writeValidConfigFiles(t *testing.T, workspaceRoot string, transcribeURL ...
pipelineYAML := `workspace:
root: ` + workspaceRoot + `
cache:
root: ` + filepath.Join(workspaceRoot, "cache") + `
spool:
root: ` + filepath.Join(workspaceRoot, "spool") + `
storage:
backend: s3
s3:

37
internal/app/restore_execute.go
View File

@@ -9,6 +9,7 @@ import (
"gitea.maximumdirect.net/eric/narratio/internal/adapters/storage"
"gitea.maximumdirect.net/eric/narratio/internal/artifacts"
"gitea.maximumdirect.net/eric/narratio/internal/audio"
"gitea.maximumdirect.net/eric/narratio/internal/config"
"gitea.maximumdirect.net/eric/narratio/internal/manifest"
)
@@ -92,6 +93,10 @@ func executeRestoreDownloadAction(
return fmt.Errorf("restore plan local path mismatch for %q", action.LocalRelativePath)
}
if restoreActionIsAudio(action) {
return executeRestoreAudioAction(ctx, cfg, safeLocalPath, action, store)
}
tmpPath, err := downloadObjectToSiblingTemp(ctx, store, action.RemoteKey, safeLocalPath)
if err != nil {
return fmt.Errorf("download to temp file: %w", err)
@@ -120,6 +125,38 @@ func executeRestoreDownloadAction(
return nil
}
func executeRestoreAudioAction(
ctx context.Context,
cfg *config.Config,
safeLocalPath string,
action RestoreAction,
store storage.ObjectStore,
) error {
if cfg == nil || cfg.Pipeline == nil || cfg.Pipeline.Storage.S3 == nil || cfg.Session == nil {
return fmt.Errorf("resolved s3 config and session are required")
}
spoolDir := artifacts.SessionSpoolRestoreAudioDir(cfg.Pipeline.Spool.Root, cfg.Session.Campaign, cfg.Session.SessionID)
spoolPath := filepath.Join(spoolDir, filepath.Base(safeLocalPath))
cacheEnabled := cfg.Pipeline.Cache.S3Audio == nil || *cfg.Pipeline.Cache.S3Audio
_, err := audio.MaterializeS3Audio(ctx, audio.S3MaterializeRequest{
Store: store,
Object: storage.ObjectInfo{
Key: action.RemoteKey,
Size: action.Size,
ETag: action.ETag,
},
Bucket: strings.TrimSpace(cfg.Pipeline.Storage.S3.Bucket),
CacheRoot: strings.TrimSpace(cfg.Pipeline.Cache.Root),
CacheEnabled: cacheEnabled,
SpoolPath: spoolPath,
DestPath: safeLocalPath,
})
if err != nil {
return fmt.Errorf("materialize audio: %w", err)
}
return nil
}
func downloadObjectToSiblingTemp(ctx context.Context, store storage.ObjectStore, remoteKey, destPath string) (string, error) {
if strings.TrimSpace(destPath) == "" {
return "", fmt.Errorf("destination path is required")

48
internal/app/restore_execution_test.go
View File

@@ -87,6 +87,44 @@ func TestExecuteRestoreIncludeAudioRestoresAudio(t *testing.T) {
}
}
func TestExecuteRestoreIncludeAudioUsesCacheAfterWorkspaceDeletion(t *testing.T) {
workspaceRoot := t.TempDir()
pipelinePath, campaignPath, sessionPath := writeValidConfigFiles(t, workspaceRoot)
fake := &storage.FakeBackend{}
cfg, sessionPrefix, _, _ := seedRestoreCommittedState(t, fake, pipelinePath, campaignPath, sessionPath)
audioKey := sessionPrefix + "audio/alice.flac"
seedRestoreObject(fake, audioKey, []byte("remote-audio"))
restoreWithStoreAndRealPhases(t, fake)
var stdout bytes.Buffer
var stderr bytes.Buffer
code := Execute([]string{"restore", "--config", pipelinePath, "--campaign", campaignPath, "--session", sessionPath, "--include-audio"}, &stdout, &stderr)
if code != 0 {
t.Fatalf("first restore exit code = %d, want 0; stderr=%q", code, stderr.String())
}
if got := fakeDownloadCount(fake, audioKey); got != 1 {
t.Fatalf("audio downloads after first restore = %d, want 1", got)
}
sessionRoot := artifacts.SessionWorkDirForCampaign(workspaceRoot, cfg.Session.Campaign, cfg.Session.SessionID)
mustReadEquals(t, filepath.Join(sessionRoot, "audio", "alice.flac"), "remote-audio")
if err := os.RemoveAll(sessionRoot); err != nil {
t.Fatalf("remove session root: %v", err)
}
stdout.Reset()
stderr.Reset()
code = Execute([]string{"restore", "--config", pipelinePath, "--campaign", campaignPath, "--session", sessionPath, "--include-audio"}, &stdout, &stderr)
if code != 0 {
t.Fatalf("second restore exit code = %d, want 0; stderr=%q", code, stderr.String())
}
if got := fakeDownloadCount(fake, audioKey); got != 1 {
t.Fatalf("audio downloads after cached restore = %d, want still 1", got)
}
mustReadEquals(t, filepath.Join(sessionRoot, "audio", "alice.flac"), "remote-audio")
}
func TestExecuteRestoreRestoresPreviousCacheWhenPresent(t *testing.T) {
workspaceRoot := t.TempDir()
pipelinePath, campaignPath, sessionPath := writeValidConfigFiles(t, workspaceRoot)
@@ -374,6 +412,16 @@ func mustReadEquals(t *testing.T, path, want string) {
}
}
func fakeDownloadCount(fake *storage.FakeBackend, key string) int {
count := 0
for _, call := range fake.Downloads {
if call.Key == key {
count++
}
}
return count
}
type stagedManifestDownloadStore struct {
delegate *storage.FakeBackend
manifestKey string

38
internal/app/restore_plan.go
View File

@@ -257,6 +257,35 @@ func classifyRestoreAction(
return action, nil
}
if restoreRelativePathIsAudio(localRelPath) {
if object.Size > 0 {
if info.Size() == object.Size {
action.Kind = RestoreActionSkipSame
action.SameLocal = true
action.Reason = "local audio size matches remote content"
return action, nil
}
if force {
action.Kind = RestoreActionDownload
action.Reason = "local audio differs (size mismatch); overwrite with --force"
return action, nil
}
action.Kind = RestoreActionConflict
action.Conflict = true
action.Reason = "local audio differs (size mismatch)"
return action, nil
}
if force {
action.Kind = RestoreActionDownload
action.Reason = "local audio exists; remote size unavailable; overwrite with --force"
return action, nil
}
action.Kind = RestoreActionConflict
action.Conflict = true
action.Reason = "local audio exists; remote size unavailable"
return action, nil
}
if object.Size > 0 && info.Size() != object.Size {
if force {
action.Kind = RestoreActionDownload
@@ -303,6 +332,15 @@ func classifyRestoreAction(
return action, nil
}
func restoreActionIsAudio(action RestoreAction) bool {
return restoreRelativePathIsAudio(action.LocalRelativePath)
}
func restoreRelativePathIsAudio(rel string) bool {
cleanRel := path.Clean(strings.TrimSpace(rel))
return cleanRel == config.PathAudioDirSegment || strings.HasPrefix(cleanRel, config.PathAudioDirSegment+"/")
}
func writeRestorePlan(out io.Writer, current *RemoteCurrentState, plan *RestorePlan, opts RestorePlanOptions) error {
if out == nil {
return fmt.Errorf("output writer is required")

27
internal/app/restore_plan_test.go
View File

@@ -58,6 +58,33 @@ func TestRestorePlanIncludeAudio(t *testing.T) {
}
}
func TestRestorePlanExistingAudioUsesSizeWithoutRemoteChecksumDownload(t *testing.T) {
cfg := restorePlanConfig(t)
current := restorePlanCurrentState(t, cfg)
store := &storage.FakeBackend{}
seedRestoreObject(store, current.CurrentManifestKey, []byte(`{"session_id":"2026-05-03"}`))
seedRestoreObject(store, current.SessionPrefix+"audio/alice.flac", []byte("audio"))
sessionRoot := artifacts.SessionWorkDirForCampaign(cfg.Pipeline.Workspace.Root, cfg.Session.Campaign, cfg.Session.SessionID)
mustWriteTestFile(t, filepath.Join(sessionRoot, "audio", "alice.flac"), "local")
plan, err := buildRestorePlan(context.Background(), cfg, current, store, RestorePlanOptions{IncludeAudio: true})
if err != nil {
t.Fatalf("buildRestorePlan() error = %v", err)
}
if len(store.Downloads) != 0 {
t.Fatalf("downloads = %d, want no remote checksum download for audio", len(store.Downloads))
}
actionByRel := map[string]RestoreAction{}
for _, action := range plan.Actions {
actionByRel[action.LocalRelativePath] = action
}
audioAction := actionByRel["audio/alice.flac"]
if audioAction.Kind != RestoreActionSkipSame {
t.Fatalf("audio action kind = %q, want %q", audioAction.Kind, RestoreActionSkipSame)
}
}
func TestRestorePlanIncludesPreviousCacheByDefault(t *testing.T) {
cfg := restorePlanConfig(t)
current := restorePlanCurrentState(t, cfg)