Add post-archive cleanup policies

This commit is contained in:
2026-05-16 23:09:39 +00:00
parent 6fbefb9867
commit d5a9ad38f8
11 changed files with 639 additions and 5 deletions

View File

@@ -83,6 +83,7 @@ Implemented foundations:
Current defaults:
- `pipeline.storage.s3.root_prefix`: `dnd`
- `pipeline.workspace.cleanup_after_archive`: `false`
- `pipeline.spool.root`: `/var/spool/narratio`
- `pipeline.spool.delete_audio_after_archive`: `false`
- `pipeline.archive.enabled`: `true`
@@ -104,6 +105,12 @@ Current boundaries:
- archive uploads `current/run_id.txt` last as the effective commit marker
- required missing promotions fail archive
- optional missing promotions are skipped and recorded
- cleanup remains conservative and opt-in:
- `pipeline.spool.delete_audio_after_archive: true` removes only the run-scoped spool audio directory after successful archive commit
- `pipeline.workspace.cleanup_after_archive: true` removes only the run-scoped local workdir after successful archive commit
- cleanup executes only after all selected stages for the command invocation succeed
- cleanup does not run for failed, incomplete, skipped, or unarchived runs
- local development `audio_dir`/`audio_files` source inputs are never deleted by spool cleanup
S3 input details and current boundaries are documented in [docs/s3-audio-input.md](docs/s3-audio-input.md).

View File

@@ -152,7 +152,8 @@ Storage and archive foundations:
- `endpoint`
- `force_path_style` (default `false`)
- `pipeline.spool.root` defaults to `/var/spool/narratio`
- `pipeline.spool.delete_audio_after_archive` defaults to `false` (cleanup behavior not implemented yet)
- `pipeline.workspace.cleanup_after_archive` defaults to `false`
- `pipeline.spool.delete_audio_after_archive` defaults to `false`
- `pipeline.archive` is optional and defaults to:
- `enabled: true`
- `upload_run: true`
@@ -230,6 +231,13 @@ Archive publishing behavior (implemented):
- `current/run_id.txt` is the effective commit marker
- if promotion or current-manifest upload fails, archive returns failure and does not write `current/run_id.txt`
- failed/incomplete runs remain local and are not uploaded
- post-archive local cleanup (implemented, opt-in):
- cleanup runs only after archive succeeded and wrote `current/run_id.txt`
- cleanup is executed after all selected stages in the command invocation succeed (for example, a later `notify` failure leaves local files intact)
- `pipeline.spool.delete_audio_after_archive: true` removes only `{spool.root}/{campaign}/{session_id}/{run_id}/audio/`
- `pipeline.workspace.cleanup_after_archive: true` removes only `{workspace.root}/work/{campaign}/{session_id}/{run_id}/`
- cleanup does not run when archive is skipped/disabled/fails or when run upload is disabled
- local development `audio_dir`/`audio_files` inputs are never removed by spool cleanup
`pipeline.scriptorium` is optional. Existing pipelines without Scriptorium continue to work.

View File

@@ -20,11 +20,13 @@ Implemented:
- archive uploads configured promoted outputs to session-level keys.
- archive uploads `current/manifest.json`.
- archive uploads `current/run_id.txt` last as the effective commit marker.
- optional post-archive local cleanup:
- `pipeline.spool.delete_audio_after_archive: true` removes only the run-scoped spool audio directory
- `pipeline.workspace.cleanup_after_archive: true` removes only the run-scoped local workdir
- tests use fake storage and do not require live S3.
Future work:
- spool audio cleanup/deletion behavior
- `notify` stage behavior
- stale detection
- optional future source-audio upload mode
@@ -89,6 +91,7 @@ Archive writes:
Writing `current/run_id.txt` last makes it the effective commit marker for published session state.
If any required run upload, promotion upload, or current-manifest upload fails, archive returns failure and does not write `current/run_id.txt`.
Cleanup runs only after this commit-marker write has succeeded.
## Audio Upload Policy
@@ -99,6 +102,7 @@ Original audio is expected at the session-level audio prefix and is not duplicat
- `archive.enabled: false` skips archive cleanly.
- `archive.upload_run: false` skips run upload cleanly.
- both skip cases also skip post-archive local cleanup.
## Metadata

View File

@@ -120,10 +120,13 @@ Implemented in repository:
- `current/run_id.txt` is uploaded last as the effective commit marker
- current pointer content is `{run_id}` plus trailing newline
- if promotion/current manifest upload fails, current pointer is not written
- post-archive local cleanup behavior:
- `pipeline.spool.delete_audio_after_archive` removes run-scoped spool audio only after successful archive commit
- `pipeline.workspace.cleanup_after_archive` removes run-scoped workdir only after successful archive commit
- cleanup is skipped for failed/incomplete/skipped/unarchived runs
Not implemented yet:
- spool audio cleanup / deletion behavior
- `notify` stage behavior
- generic stale detection based on input/config checksums
- optional future mode for uploading source audio from local workspace/spool

View File

@@ -12,7 +12,6 @@ Implemented:
Not implemented:
- spool cleanup/deletion behavior
- uploads of failed runs
## Required Configuration

View File

@@ -1,5 +1,6 @@
workspace:
root: ./tmp/narratio-workspace
cleanup_after_archive: false
storage:
backend: local

View File

@@ -0,0 +1,208 @@
package app
import (
"context"
"fmt"
"os"
"path/filepath"
"strings"
"gitea.maximumdirect.net/eric/narratio/internal/artifacts"
"gitea.maximumdirect.net/eric/narratio/internal/config"
"gitea.maximumdirect.net/eric/narratio/internal/manifest"
)
func runPostArchiveCleanup(ctx context.Context, env *Env, manifestPath string, m *manifest.Manifest, executed []string) error {
if env == nil || env.Config == nil || env.Config.Pipeline == nil || m == nil {
return nil
}
spoolRequested := env.Config.Pipeline.Spool.DeleteAudioAfterArchive
workRequested := env.Config.Pipeline.Workspace.CleanupAfterArchive
if !spoolRequested && !workRequested {
return nil
}
sr := archiveStageRecordForCleanup(m, executed)
if sr == nil {
return nil
}
if sr.Metadata == nil {
sr.Metadata = map[string]any{}
}
sr.Metadata["spool_cleanup_requested"] = spoolRequested
sr.Metadata["workdir_cleanup_requested"] = workRequested
eligible, reason := archiveCleanupEligible(env.Config, sr)
if !eligible {
sr.Metadata["cleanup_skipped"] = true
sr.Metadata["cleanup_skipped_reason"] = reason
if err := env.ManifestStore.Save(ctx, manifestPath, m); err != nil {
return fmt.Errorf("save manifest cleanup skip metadata %q: %w", manifestPath, err)
}
return nil
}
spoolDir := strings.TrimSpace(m.LocalSpoolDir)
if spoolDir == "" {
spoolDir = artifacts.SessionSpoolAudioDir(
env.Config.Pipeline.Spool.Root,
strings.TrimSpace(env.Config.Session.Campaign),
strings.TrimSpace(env.Config.Session.SessionID),
strings.TrimSpace(m.RunID),
)
}
workDir := strings.TrimSpace(m.LocalWorkDir)
if workDir == "" {
workDir = artifacts.SessionRunWorkDir(
env.Config.Pipeline.Workspace.Root,
strings.TrimSpace(env.Config.Session.Campaign),
strings.TrimSpace(env.Config.Session.SessionID),
strings.TrimSpace(m.RunID),
)
}
if spoolRequested {
if err := removeRunScopedDir(strings.TrimSpace(env.Config.Pipeline.Spool.Root), spoolDir, "pipeline.spool.delete_audio_after_archive"); err != nil {
sr.Metadata["cleanup_failed"] = true
sr.Metadata["cleanup_failed_policy"] = "pipeline.spool.delete_audio_after_archive"
sr.Metadata["cleanup_failed_path"] = spoolDir
_ = env.ManifestStore.Save(ctx, manifestPath, m)
return err
}
sr.Metadata["spool_cleanup_deleted"] = filepath.Clean(spoolDir)
}
if !workRequested {
sr.Metadata["cleanup_completed"] = true
sr.Metadata["cleanup_skipped"] = false
if err := env.ManifestStore.Save(ctx, manifestPath, m); err != nil {
return fmt.Errorf("save manifest cleanup metadata %q: %w", manifestPath, err)
}
return nil
}
if err := removeRunScopedDir(strings.TrimSpace(env.Config.Pipeline.Workspace.Root), workDir, "pipeline.workspace.cleanup_after_archive"); err != nil {
sr.Metadata["cleanup_failed"] = true
sr.Metadata["cleanup_failed_policy"] = "pipeline.workspace.cleanup_after_archive"
sr.Metadata["cleanup_failed_path"] = workDir
_ = env.ManifestStore.Save(ctx, manifestPath, m)
return err
}
sr.Metadata["workdir_cleanup_deleted"] = filepath.Clean(workDir)
sr.Metadata["cleanup_completed"] = true
sr.Metadata["cleanup_skipped"] = false
return nil
}
func archiveStageRecordForCleanup(m *manifest.Manifest, executed []string) *manifest.StageRecord {
if m == nil {
return nil
}
archiveRan := false
for _, name := range executed {
if name == "archive" {
archiveRan = true
break
}
}
if !archiveRan {
return nil
}
sr := m.Stages["archive"]
if sr == nil || sr.Status != manifest.StatusSucceeded {
return nil
}
return sr
}
func archiveCleanupEligible(cfg *config.Config, sr *manifest.StageRecord) (bool, string) {
if cfg == nil || cfg.Pipeline == nil || cfg.Pipeline.Archive == nil {
return false, "archive configuration is missing"
}
enabled := true
if cfg.Pipeline.Archive.Enabled != nil {
enabled = *cfg.Pipeline.Archive.Enabled
}
if !enabled {
return false, "archive.enabled is false"
}
uploadRun := true
if cfg.Pipeline.Archive.UploadRun != nil {
uploadRun = *cfg.Pipeline.Archive.UploadRun
}
if !uploadRun {
return false, "archive.upload_run is false"
}
if sr == nil || sr.Metadata == nil {
return false, "archive metadata is missing"
}
if skipped, _ := sr.Metadata["skipped"].(bool); skipped {
return false, "archive stage was skipped"
}
if uploaded, _ := sr.Metadata["uploaded"].(bool); !uploaded {
return false, "archive did not upload run record"
}
if pointer, _ := sr.Metadata["current_pointer_written"].(bool); !pointer {
return false, "archive did not write current pointer"
}
if strings.TrimSpace(asString(sr.Metadata["current_run_id_key"])) == "" {
return false, "archive current run pointer key is missing"
}
return true, ""
}
func removeRunScopedDir(root, target, policy string) error {
cleanRoot := strings.TrimSpace(root)
cleanTarget := strings.TrimSpace(target)
if cleanRoot == "" {
return fmt.Errorf("cleanup policy %s: root path is required", policy)
}
if cleanTarget == "" {
return fmt.Errorf("cleanup policy %s: target path is required", policy)
}
rootAbs, err := filepath.Abs(cleanRoot)
if err != nil {
return fmt.Errorf("cleanup policy %s: resolve root %q: %w", policy, cleanRoot, err)
}
targetAbs, err := filepath.Abs(cleanTarget)
if err != nil {
return fmt.Errorf("cleanup policy %s: resolve target %q: %w", policy, cleanTarget, err)
}
rel, err := filepath.Rel(rootAbs, targetAbs)
if err != nil {
return fmt.Errorf("cleanup policy %s: relative path from %q to %q: %w", policy, rootAbs, targetAbs, err)
}
if rel == "." {
return fmt.Errorf("cleanup policy %s: refusing to delete root directory %q", policy, rootAbs)
}
if rel == ".." || strings.HasPrefix(rel, ".."+string(filepath.Separator)) {
return fmt.Errorf("cleanup policy %s: refusing to delete path outside root: root=%q target=%q", policy, rootAbs, targetAbs)
}
info, err := os.Lstat(targetAbs)
if err != nil {
if os.IsNotExist(err) {
return nil
}
return fmt.Errorf("cleanup policy %s: stat target %q: %w", policy, targetAbs, err)
}
if info.Mode()&os.ModeSymlink != 0 {
return fmt.Errorf("cleanup policy %s: refusing to delete symlink path %q", policy, targetAbs)
}
if !info.IsDir() {
return fmt.Errorf("cleanup policy %s: target %q is not a directory", policy, targetAbs)
}
if err := os.RemoveAll(targetAbs); err != nil {
return fmt.Errorf("cleanup policy %s: remove %q: %w", policy, targetAbs, err)
}
return nil
}
func asString(v any) string {
s, _ := v.(string)
return s
}

View File

@@ -0,0 +1,396 @@
package app
import (
"context"
"errors"
"os"
"path/filepath"
"strings"
"testing"
"time"
"gitea.maximumdirect.net/eric/narratio/internal/adapters/storage"
"gitea.maximumdirect.net/eric/narratio/internal/artifacts"
"gitea.maximumdirect.net/eric/narratio/internal/config"
"gitea.maximumdirect.net/eric/narratio/internal/manifest"
"gitea.maximumdirect.net/eric/narratio/internal/stage"
)
type archiveSuccessStage struct {
metadata map[string]any
}
func (archiveSuccessStage) Name() string { return "archive" }
func (archiveSuccessStage) Declares() stage.IODecl { return stage.IODecl{} }
func (s archiveSuccessStage) Run(_ context.Context, _ *stage.Env, _ *manifest.Manifest) (*stage.StageResult, error) {
md := map[string]any{
"stage": "archive",
"uploaded": true,
"current_pointer_written": true,
"current_run_id_key": "dnd/campaigns/sample-campaign/sessions/2026-05-03/current/run_id.txt",
}
for k, v := range s.metadata {
md[k] = v
}
return &stage.StageResult{Metadata: md}, nil
}
type notifyFailStage struct{}
func (notifyFailStage) Name() string { return "notify" }
func (notifyFailStage) Declares() stage.IODecl { return stage.IODecl{} }
func (notifyFailStage) Run(_ context.Context, _ *stage.Env, _ *manifest.Manifest) (*stage.StageResult, error) {
return nil, errors.New("notify failed")
}
func TestPostArchiveCleanupDisabledKeepsLocalDirs(t *testing.T) {
cfg, seed := cleanupFixtureConfig(t)
cfg.Pipeline.Spool.DeleteAudioAfterArchive = false
cfg.Pipeline.Workspace.CleanupAfterArchive = false
if _, err := executeStages(context.Background(), cfg, []stage.Stage{archiveSuccessStage{}}, RunOptions{Env: &Env{ObjectStore: &storage.FakeBackend{}}}); err != nil {
t.Fatalf("executeStages() error = %v", err)
}
assertExists(t, seed.spoolAudioDir)
assertExists(t, seed.runWorkDir)
assertExists(t, seed.localSourceAudio)
}
func TestPostArchiveCleanupSpoolOnly(t *testing.T) {
cfg, seed := cleanupFixtureConfig(t)
cfg.Pipeline.Spool.DeleteAudioAfterArchive = true
cfg.Pipeline.Workspace.CleanupAfterArchive = false
if _, err := executeStages(context.Background(), cfg, []stage.Stage{archiveSuccessStage{}}, RunOptions{Env: &Env{ObjectStore: &storage.FakeBackend{}}}); err != nil {
t.Fatalf("executeStages() error = %v", err)
}
assertMissing(t, seed.spoolAudioDir)
assertExists(t, seed.runWorkDir)
assertExists(t, seed.localSourceAudio)
}
func TestPostArchiveCleanupWorkdirOnly(t *testing.T) {
cfg, seed := cleanupFixtureConfig(t)
cfg.Pipeline.Spool.DeleteAudioAfterArchive = false
cfg.Pipeline.Workspace.CleanupAfterArchive = true
if _, err := executeStages(context.Background(), cfg, []stage.Stage{archiveSuccessStage{}}, RunOptions{Env: &Env{ObjectStore: &storage.FakeBackend{}}}); err != nil {
t.Fatalf("executeStages() error = %v", err)
}
assertExists(t, cfg.Pipeline.Workspace.Root)
assertExists(t, seed.otherRunDir)
assertMissing(t, seed.runWorkDir)
assertExists(t, seed.spoolAudioDir)
}
func TestPostArchiveCleanupBothPolicies(t *testing.T) {
cfg, seed := cleanupFixtureConfig(t)
cfg.Pipeline.Spool.DeleteAudioAfterArchive = true
cfg.Pipeline.Workspace.CleanupAfterArchive = true
if _, err := executeStages(context.Background(), cfg, []stage.Stage{archiveSuccessStage{}}, RunOptions{Env: &Env{ObjectStore: &storage.FakeBackend{}}}); err != nil {
t.Fatalf("executeStages() error = %v", err)
}
assertMissing(t, seed.spoolAudioDir)
assertMissing(t, seed.runWorkDir)
assertExists(t, seed.otherRunDir)
}
func TestPostArchiveCleanupNotRunWhenArchiveFails(t *testing.T) {
cfg, seed := cleanupFixtureConfig(t)
cfg.Pipeline.Spool.DeleteAudioAfterArchive = true
cfg.Pipeline.Workspace.CleanupAfterArchive = true
_, err := executeStages(context.Background(), cfg, []stage.Stage{failingStage{name: "archive", err: errors.New("archive failed")}}, RunOptions{Env: &Env{ObjectStore: &storage.FakeBackend{}}})
if err == nil || !strings.Contains(err.Error(), "stage \"archive\" failed") {
t.Fatalf("executeStages() error = %v, want archive failure", err)
}
assertExists(t, seed.spoolAudioDir)
assertExists(t, seed.runWorkDir)
}
func TestPostArchiveCleanupNotRunWhenArchiveSkipped(t *testing.T) {
cfg, seed := cleanupFixtureConfig(t)
cfg.Pipeline.Spool.DeleteAudioAfterArchive = true
cfg.Pipeline.Workspace.CleanupAfterArchive = true
if _, err := executeStages(context.Background(), cfg, []stage.Stage{archiveSuccessStage{metadata: map[string]any{"skipped": true}}}, RunOptions{Env: &Env{ObjectStore: &storage.FakeBackend{}}}); err != nil {
t.Fatalf("executeStages() error = %v", err)
}
assertExists(t, seed.spoolAudioDir)
assertExists(t, seed.runWorkDir)
}
func TestPostArchiveCleanupNotRunWhenCurrentPointerMissing(t *testing.T) {
cfg, seed := cleanupFixtureConfig(t)
cfg.Pipeline.Spool.DeleteAudioAfterArchive = true
cfg.Pipeline.Workspace.CleanupAfterArchive = true
if _, err := executeStages(context.Background(), cfg, []stage.Stage{archiveSuccessStage{metadata: map[string]any{"current_pointer_written": false}}}, RunOptions{Env: &Env{ObjectStore: &storage.FakeBackend{}}}); err != nil {
t.Fatalf("executeStages() error = %v", err)
}
assertExists(t, seed.spoolAudioDir)
assertExists(t, seed.runWorkDir)
}
func TestPostArchiveCleanupNotRunWhenArchiveUploadDisabled(t *testing.T) {
cfg, seed := cleanupFixtureConfig(t)
cfg.Pipeline.Spool.DeleteAudioAfterArchive = true
cfg.Pipeline.Workspace.CleanupAfterArchive = true
cfg.Pipeline.Archive.UploadRun = boolPtr(false)
if _, err := executeStages(context.Background(), cfg, []stage.Stage{archiveSuccessStage{}}, RunOptions{Env: &Env{ObjectStore: &storage.FakeBackend{}}}); err != nil {
t.Fatalf("executeStages() error = %v", err)
}
assertExists(t, seed.spoolAudioDir)
assertExists(t, seed.runWorkDir)
}
func TestPostArchiveCleanupWaitsUntilAllStagesSucceed(t *testing.T) {
cfg, seed := cleanupFixtureConfig(t)
cfg.Pipeline.Spool.DeleteAudioAfterArchive = true
cfg.Pipeline.Workspace.CleanupAfterArchive = true
_, err := executeStages(context.Background(), cfg, []stage.Stage{archiveSuccessStage{}, notifyFailStage{}}, RunOptions{Env: &Env{ObjectStore: &storage.FakeBackend{}}})
if err == nil || !strings.Contains(err.Error(), "stage \"notify\" failed") {
t.Fatalf("executeStages() error = %v, want notify failure", err)
}
assertExists(t, seed.spoolAudioDir)
assertExists(t, seed.runWorkDir)
}
func TestPostArchiveCleanupFailsOnUnsafePath(t *testing.T) {
cfg, _ := cleanupFixtureConfig(t)
cfg.Pipeline.Spool.DeleteAudioAfterArchive = true
cfg.Pipeline.Workspace.CleanupAfterArchive = false
manifestPath := manifestPathFor(cfg)
store := &manifest.LocalStore{}
m, err := store.Load(context.Background(), manifestPath)
if err != nil {
t.Fatalf("Load() error = %v", err)
}
m.LocalSpoolDir = filepath.Join(filepath.Dir(cfg.Pipeline.Spool.Root), "outside-spool")
if err := store.Save(context.Background(), manifestPath, m); err != nil {
t.Fatalf("Save() error = %v", err)
}
_, err = executeStages(context.Background(), cfg, []stage.Stage{archiveSuccessStage{}}, RunOptions{Env: &Env{ObjectStore: &storage.FakeBackend{}}})
if err == nil || !strings.Contains(err.Error(), "refusing to delete path outside root") {
t.Fatalf("executeStages() error = %v, want safe-path failure", err)
}
}
func TestPostArchiveCleanupNotRunWhenPromotionIsMissing(t *testing.T) {
cfg, seed, runID := archiveStageCleanupFixture(t)
cfg.Pipeline.Spool.DeleteAudioAfterArchive = true
cfg.Pipeline.Workspace.CleanupAfterArchive = true
cfg.Pipeline.Archive.PromoteArtifacts = []config.ArchivePromotionRule{
{From: "artifacts/missing.md", To: "artifacts/missing.md", Required: boolPtr(true)},
}
archiveStageImpl, err := stage.Select("archive")
if err != nil {
t.Fatalf("Select(archive) error = %v", err)
}
_, err = executeStages(context.Background(), cfg, []stage.Stage{archiveStageImpl}, RunOptions{Env: &Env{ObjectStore: &storage.FakeBackend{}}})
if err == nil || !strings.Contains(err.Error(), "required promotion source missing") {
t.Fatalf("executeStages() error = %v, want promotion-missing failure", err)
}
assertExists(t, seed.spoolAudioDir)
assertExists(t, seed.runWorkDir)
assertExists(t, filepath.Join(seed.runWorkDir, "manifest.json"))
assertExists(t, artifacts.SessionRunWorkDir(cfg.Pipeline.Workspace.Root, cfg.Session.Campaign, cfg.Session.SessionID, runID))
}
func TestPostArchiveCleanupNotRunWhenCurrentManifestUploadFails(t *testing.T) {
cfg, seed, _ := archiveStageCleanupFixture(t)
cfg.Pipeline.Spool.DeleteAudioAfterArchive = true
cfg.Pipeline.Workspace.CleanupAfterArchive = true
failKey := seed.sessionPrefix + "current/manifest.json"
archiveStageImpl, err := stage.Select("archive")
if err != nil {
t.Fatalf("Select(archive) error = %v", err)
}
_, err = executeStages(context.Background(), cfg, []stage.Stage{archiveStageImpl}, RunOptions{
Env: &Env{ObjectStore: &failKeyStore{delegate: &storage.FakeBackend{}, failKey: failKey}},
})
if err == nil || !strings.Contains(err.Error(), "current manifest") {
t.Fatalf("executeStages() error = %v, want current-manifest failure", err)
}
assertExists(t, seed.spoolAudioDir)
assertExists(t, seed.runWorkDir)
}
func TestPostArchiveCleanupNotRunWhenCurrentPointerUploadFails(t *testing.T) {
cfg, seed, _ := archiveStageCleanupFixture(t)
cfg.Pipeline.Spool.DeleteAudioAfterArchive = true
cfg.Pipeline.Workspace.CleanupAfterArchive = true
failKey := seed.sessionPrefix + "current/run_id.txt"
archiveStageImpl, err := stage.Select("archive")
if err != nil {
t.Fatalf("Select(archive) error = %v", err)
}
_, err = executeStages(context.Background(), cfg, []stage.Stage{archiveStageImpl}, RunOptions{
Env: &Env{ObjectStore: &failKeyStore{delegate: &storage.FakeBackend{}, failKey: failKey}},
})
if err == nil || !strings.Contains(err.Error(), "current run pointer") {
t.Fatalf("executeStages() error = %v, want current-run-pointer failure", err)
}
assertExists(t, seed.spoolAudioDir)
assertExists(t, seed.runWorkDir)
}
type cleanupSeed struct {
runWorkDir string
otherRunDir string
spoolAudioDir string
localSourceAudio string
sessionPrefix string
}
func cleanupFixtureConfig(t *testing.T) (*config.Config, cleanupSeed) {
t.Helper()
cfg := testConfig(t)
cfg.Pipeline.Archive = &config.ArchiveConfig{Enabled: boolPtr(true), UploadRun: boolPtr(true)}
cfg.Pipeline.Spool.Root = filepath.Join(t.TempDir(), "spool")
runID := "20260516T010203Z-1a2b3c4d"
runWorkDir := artifacts.SessionRunWorkDir(cfg.Pipeline.Workspace.Root, cfg.Session.Campaign, cfg.Session.SessionID, runID)
otherRunDir := artifacts.SessionRunWorkDir(cfg.Pipeline.Workspace.Root, cfg.Session.Campaign, cfg.Session.SessionID, "20260516T010204Z-5e6f7a8b")
spoolAudioDir := artifacts.SessionSpoolAudioDir(cfg.Pipeline.Spool.Root, cfg.Session.Campaign, cfg.Session.SessionID, runID)
mustWriteFile(t, filepath.Join(runWorkDir, "manifest.json"), "{}\n")
mustWriteFile(t, filepath.Join(runWorkDir, "logs", "stage.log"), "log\n")
mustWriteFile(t, filepath.Join(otherRunDir, "logs", "stage.log"), "other\n")
mustWriteFile(t, filepath.Join(spoolAudioDir, "speaker.flac"), "flac\n")
localSourceAudio := filepath.Join(filepath.Dir(cfg.SessionPath), "audio", "alice.flac")
mustWriteFile(t, localSourceAudio, "source\n")
seed := manifest.New(cfg.Session.SessionID, time.Now().UTC())
seed.Campaign = cfg.Session.Campaign
seed.RunID = runID
seed.LocalWorkDir = runWorkDir
seed.LocalSpoolDir = spoolAudioDir
seed.S3Bucket = "my-dnd-archive"
seed.S3SessionPrefix = "dnd/campaigns/sample-campaign/sessions/2026-05-03/"
seed.S3RunPrefix = seed.S3SessionPrefix + "runs/" + runID + "/"
store := &manifest.LocalStore{}
if err := os.MkdirAll(filepath.Dir(manifestPathFor(cfg)), 0o755); err != nil {
t.Fatalf("MkdirAll() error = %v", err)
}
if err := store.Save(context.Background(), manifestPathFor(cfg), seed); err != nil {
t.Fatalf("seed manifest save error = %v", err)
}
return cfg, cleanupSeed{
runWorkDir: runWorkDir,
otherRunDir: otherRunDir,
spoolAudioDir: spoolAudioDir,
localSourceAudio: localSourceAudio,
sessionPrefix: seed.S3SessionPrefix,
}
}
func archiveStageCleanupFixture(t *testing.T) (*config.Config, cleanupSeed, string) {
t.Helper()
cfg, seed := cleanupFixtureConfig(t)
runID := "20260516T010203Z-1a2b3c4d"
cfg.Pipeline.Storage.S3 = &config.StorageS3Config{
Bucket: "my-dnd-archive",
RootPrefix: "dnd",
}
cfg.Pipeline.Archive = &config.ArchiveConfig{
Enabled: boolPtr(true),
UploadRun: boolPtr(true),
PromoteArtifacts: []config.ArchivePromotionRule{
{From: "transcripts/trimmed.json", To: "transcripts/trimmed.json", Required: boolPtr(true)},
{From: "artifacts/session_recap.md", To: "artifacts/session_recap.md", Required: boolPtr(true)},
},
}
writeArchiveFixtureRunFiles(t, seed.runWorkDir)
store := &manifest.LocalStore{}
seedManifest, err := store.Load(context.Background(), manifestPathFor(cfg))
if err != nil {
t.Fatalf("Load() error = %v", err)
}
for _, name := range []string{"prepare", "transcribe", "merge", "polish", "normalize", "trim", "analyze"} {
seedManifest.MarkStageSucceeded(name, time.Now().UTC(), nil)
}
seedManifest.S3SessionPrefix = artifacts.S3SessionPrefix("dnd", cfg.Session.Campaign, cfg.Session.SessionID)
seedManifest.S3RunPrefix = artifacts.S3RunPrefix(seedManifest.S3SessionPrefix, runID)
if err := store.Save(context.Background(), manifestPathFor(cfg), seedManifest); err != nil {
t.Fatalf("Save() error = %v", err)
}
seed.sessionPrefix = seedManifest.S3SessionPrefix
return cfg, seed, runID
}
func writeArchiveFixtureRunFiles(t *testing.T, runWorkDir string) {
t.Helper()
mustWriteFile(t, filepath.Join(runWorkDir, "inputs", "session.yml"), "session_id: 2026-05-03\n")
mustWriteFile(t, filepath.Join(runWorkDir, "transcripts", "raw", "speaker.json"), "{}\n")
mustWriteFile(t, filepath.Join(runWorkDir, "transcripts", "trimmed.json"), "{}\n")
mustWriteFile(t, filepath.Join(runWorkDir, "artifacts", "session_recap.md"), "# recap\n")
mustWriteFile(t, filepath.Join(runWorkDir, "reports", "audita.report.json"), "{}\n")
mustWriteFile(t, filepath.Join(runWorkDir, "config", "audita.generated.yml"), "key: value\n")
mustWriteFile(t, filepath.Join(runWorkDir, "logs", "audita.stderr.log"), "stderr\n")
mustWriteFile(t, filepath.Join(runWorkDir, "manifest.json"), "{}\n")
}
type failKeyStore struct {
delegate *storage.FakeBackend
failKey string
}
func (s *failKeyStore) List(ctx context.Context, prefix string) ([]storage.ObjectInfo, error) {
return s.delegate.List(ctx, prefix)
}
func (s *failKeyStore) Download(ctx context.Context, key, localPath string) error {
return s.delegate.Download(ctx, key, localPath)
}
func (s *failKeyStore) Upload(ctx context.Context, localPath, key string, opts storage.UploadOptions) (storage.ObjectInfo, error) {
if strings.TrimSpace(key) == strings.TrimSpace(s.failKey) {
return storage.ObjectInfo{}, errors.New("forced upload failure")
}
return s.delegate.Upload(ctx, localPath, key, opts)
}
func (s *failKeyStore) Exists(ctx context.Context, key string) (bool, error) {
return s.delegate.Exists(ctx, key)
}
func assertExists(t *testing.T, path string) {
t.Helper()
if _, err := os.Stat(path); err != nil {
t.Fatalf("expected path to exist %q: %v", path, err)
}
}
func assertMissing(t *testing.T, path string) {
t.Helper()
if _, err := os.Stat(path); !os.IsNotExist(err) {
t.Fatalf("expected path to be removed %q, stat err=%v", path, err)
}
}

View File

@@ -168,6 +168,10 @@ func executeStages(ctx context.Context, cfg *config.Config, stages []stage.Stage
env.Logger.Info("stage succeeded", "stage", s.Name())
}
if err := runPostArchiveCleanup(ctx, env, manifestPath, m, executed); err != nil {
return nil, fmt.Errorf("post-archive cleanup: %w", err)
}
return &RunSummary{
SessionID: cfg.Session.SessionID,
ManifestPath: manifestPath,

View File

@@ -36,7 +36,8 @@ type SessionConfig struct {
// WorkspaceConfig configures local workspace behavior.
type WorkspaceConfig struct {
Root string `yaml:"root"`
Root string `yaml:"root"`
CleanupAfterArchive bool `yaml:"cleanup_after_archive"`
}
// SecretsConfig configures optional local filesystem secret loading.

View File

@@ -47,6 +47,9 @@ func TestSpoolAndArchiveDefaults(t *testing.T) {
if cfg.Pipeline.Spool.DeleteAudioAfterArchive {
t.Fatalf("spool.delete_audio_after_archive = true, want false")
}
if cfg.Pipeline.Workspace.CleanupAfterArchive {
t.Fatalf("workspace.cleanup_after_archive = true, want false")
}
if cfg.Pipeline.Archive == nil {
t.Fatal("archive should be initialized by defaults")
}