Add archive storage path configuration

This commit is contained in:
2026-05-16 14:11:59 +00:00
parent 58c6ab2d54
commit 0454296c81
23 changed files with 950 additions and 22 deletions

View File

@@ -208,6 +208,7 @@ notification:
timeout: 10s
`
sessionYAML := `session_id: ` + sessionID + `
campaign: sample-campaign
inputs:
audio_dir: ./audio
speakers_file: ./speakers.yml
@@ -271,6 +272,7 @@ notification:
timeout: 10s
`
sessionYAML := `session_id: 2026-05-03
campaign: sample-campaign
inputs:
audio_dir: ./audio
speakers_file: ./speakers.yml
@@ -377,6 +379,8 @@ func writeValidConfigFiles(t *testing.T, workspaceRoot string, transcribeURL ...
root: ` + workspaceRoot + `
storage:
backend: s3
s3:
bucket: test-bucket
whisperx:
transcribe_url: ` + url + `
timeout: 2s
@@ -400,6 +404,7 @@ notification:
`
sessionYAML := `session_id: 2026-05-03
campaign: sample-campaign
inputs:
audio_dir: ./audio
speakers_file: ./speakers.yml

View File

@@ -113,6 +113,7 @@ notification:
timeout: 10s
`
sessionYAML := `session_id: 2026-05-03
campaign: sample-campaign
inputs:
audio_dir: ./audio
speakers_file: ./speakers.yml

View File

@@ -104,6 +104,15 @@ func executeStages(ctx context.Context, cfg *config.Config, stages []stage.Stage
if err != nil {
return nil, err
}
identityChanged, err := ensureManifestIdentity(cfg, m)
if err != nil {
return nil, fmt.Errorf("initialize manifest identity: %w", err)
}
if identityChanged {
if err := env.ManifestStore.Save(ctx, manifestPath, m); err != nil {
return nil, fmt.Errorf("save manifest identity %q: %w", manifestPath, err)
}
}
stageEnv := env
@@ -338,6 +347,58 @@ func applyStageResultToManifest(m *manifest.Manifest, stageName string, result *
}
}
func ensureManifestIdentity(cfg *config.Config, m *manifest.Manifest) (bool, error) {
if cfg == nil || cfg.Pipeline == nil || cfg.Session == nil || m == nil {
return false, nil
}
changed := false
campaign := strings.TrimSpace(cfg.Session.Campaign)
sessionID := strings.TrimSpace(cfg.Session.SessionID)
if sessionID == "" {
sessionID = strings.TrimSpace(m.SessionID)
}
if m.Campaign == "" && campaign != "" {
m.Campaign = campaign
changed = true
}
if m.RunID == "" {
runID, err := artifacts.NewRunID()
if err != nil {
return false, err
}
m.RunID = runID
changed = true
}
if m.LocalWorkDir == "" && campaign != "" && sessionID != "" && m.RunID != "" {
m.LocalWorkDir = artifacts.SessionRunWorkDir(cfg.Pipeline.Workspace.Root, campaign, sessionID, m.RunID)
changed = true
}
if m.LocalSpoolDir == "" && campaign != "" && sessionID != "" && m.RunID != "" && strings.TrimSpace(cfg.Pipeline.Spool.Root) != "" {
m.LocalSpoolDir = artifacts.SessionSpoolAudioDir(cfg.Pipeline.Spool.Root, campaign, sessionID, m.RunID)
changed = true
}
if cfg.Pipeline.Storage.S3 != nil {
if m.S3Bucket == "" && strings.TrimSpace(cfg.Pipeline.Storage.S3.Bucket) != "" {
m.S3Bucket = strings.TrimSpace(cfg.Pipeline.Storage.S3.Bucket)
changed = true
}
sessionPrefix := artifacts.S3SessionPrefix(cfg.Pipeline.Storage.S3.RootPrefix, campaign, sessionID)
if m.S3SessionPrefix == "" && sessionPrefix != "" {
m.S3SessionPrefix = sessionPrefix
changed = true
}
runPrefix := artifacts.S3RunPrefix(sessionPrefix, m.RunID)
if m.S3RunPrefix == "" && runPrefix != "" {
m.S3RunPrefix = runPrefix
changed = true
}
}
return changed, nil
}
func manifestPathFor(cfg *config.Config) string {
return filepath.Join(cfg.Pipeline.Workspace.Root, "work", cfg.Session.SessionID, "manifest.json")
}

View File

@@ -430,7 +430,7 @@ func testConfig(t *testing.T) *config.Config {
pipelinePath := filepath.Join(cfgDir, "pipeline.yml")
mustWriteFile(t, pipelinePath, "workspace:\n root: "+workspace+"\n")
mustWriteFile(t, sessionPath, "session_id: 2026-05-03\n")
mustWriteFile(t, sessionPath, "session_id: 2026-05-03\ncampaign: sample-campaign\n")
mustWriteFile(t, filepath.Join(cfgDir, "speakers.yml"), "alice: alice.flac\n")
mustWriteFile(t, filepath.Join(cfgDir, "autocorrect.yml"), "[]\n")
mustWriteFile(t, filepath.Join(cfgDir, "glossary.yml"), "[]\n")
@@ -442,6 +442,7 @@ func testConfig(t *testing.T) *config.Config {
SessionPath: sessionPath,
Session: &config.SessionConfig{
SessionID: "2026-05-03",
Campaign: "sample-campaign",
Inputs: config.SessionInputsConfig{
AudioDir: "./audio",
SpeakersFile: "./speakers.yml",