eric/narratio
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 27 Wiki Activity

Adopt Audita v2 configuration and subprocess contract

Browse Source
This commit is contained in:
Eric Rakestraw
2026-09-25 15:45:02 +00:00
parent 7e0151ef93
commit 77d9d57937
26 changed files with 522 additions and 1260 deletions
Download Patch File Download Diff File Expand all files Collapse all files

86
internal/stage/polish.go
View File

@@ -67,39 +67,23 @@ func (polishStage) Run(ctx context.Context, env *Env, m *manifest.Manifest) (*St
if err != nil {
return nil, fmt.Errorf("polish: resolve run-local processed transcript path: %w", err)
}
canonicalReportPath := filepath.Join(paths.ArtifactsDir, "audita.report.json")
reportPath := canonicalReportPath
if runLayout.Enabled {
reportPath, err = runLocalPathForCanonical(runLayout, paths, canonicalReportPath)
if err != nil {
return nil, fmt.Errorf("polish: resolve run-local report path: %w", err)
}
}
workDir := filepath.Join(paths.ArtifactsDir, "audita-work")
stdoutPath := filepath.Join(paths.LogsDir, "audita.stdout.log")
stderrPath := filepath.Join(paths.LogsDir, "audita.stderr.log")
generatedConfigPath := filepath.Join(paths.ConfigDir, "audita.generated.yml")
if runLayout.Enabled {
workDir = filepath.Join(runLayout.ScratchDir, "audita-work")
stdoutPath = filepath.Join(runLayout.LogsDir, "audita.stdout.log")
stderrPath = filepath.Join(runLayout.LogsDir, "audita.stderr.log")
generatedConfigPath = filepath.Join(runLayout.ConfigDir, "audita.generated.yml")
}
reportEnabled := env.Config.Pipeline.Audita.Report != nil && *env.Config.Pipeline.Audita.Report
req := audita.PolishRequest{
GeneratedConfigPath: generatedConfigPath,
MergedTranscriptPath: mergedPath,
OutputProcessedPath: processedPath,
GlossaryPath: glossaryPath,
ReportPath: "",
WorkDir: workDir,
StdoutLogPath: stdoutPath,
StderrLogPath: stderrPath,
}
if reportEnabled {
req.ReportPath = reportPath
}
res, err := env.Audita.Run(ctx, req)
if err != nil {
@@ -114,16 +98,6 @@ func (polishStage) Run(ctx context.Context, env *Env, m *manifest.Manifest) (*St
return nil, fmt.Errorf("polish: processed transcript %q invalid: %w", finalProcessedPath, err)
}
finalReportPath, err := authoritativeOutputPath(req.ReportPath, res.ReportPath)
if err != nil {
return nil, fmt.Errorf("polish: %w", err)
}
if reportEnabled {
if err := validateTranscriptJSONFile(finalReportPath); err != nil {
return nil, fmt.Errorf("polish: report %q invalid: %w", finalReportPath, err)
}
}
materializedProcessed, err := materializeRunLocalOutput(env.ArtifactStore, finalProcessedPath, canonicalProcessedPath, artifacts.Ref{
Kind: "transcript_polished",
Category: "transcripts",
@@ -133,39 +107,6 @@ func (polishStage) Run(ctx context.Context, env *Env, m *manifest.Manifest) (*St
return nil, fmt.Errorf("polish: materialize canonical polished transcript: %w", err)
}
outputs := []artifacts.Ref{materializedProcessed}
if reportEnabled {
materializedReport, err := materializeRunLocalOutput(env.ArtifactStore, finalReportPath, canonicalReportPath, artifacts.Ref{
Kind: "audita_report",
Category: "artifacts",
SessionID: sessionID,
})
if err != nil {
return nil, fmt.Errorf("polish: materialize canonical report: %w", err)
}
outputs = append(outputs, materializedReport)
}
var validationConcurrency any
if env.Config.Pipeline.Audita.ValidationLLMConcurrency != nil {
validationConcurrency = *env.Config.Pipeline.Audita.ValidationLLMConcurrency
}
var totalLLMConcurrency any
if env.Config.Pipeline.Audita.TotalLLMConcurrency != nil {
totalLLMConcurrency = *env.Config.Pipeline.Audita.TotalLLMConcurrency
}
var proposalLLMConcurrency any
if env.Config.Pipeline.Audita.ProposalLLMConcurrency != nil {
proposalLLMConcurrency = *env.Config.Pipeline.Audita.ProposalLLMConcurrency
}
reportCanonicalPath := ""
if reportEnabled {
reportCanonicalPath = canonicalReportPath
}
credentialReference := ""
if env.Config.Pipeline.Audita.LLMAPIKey != nil {
credentialReference = env.Config.Pipeline.Audita.LLMAPIKey.EnvName()
}
meta := map[string]any{
"stage": "polish",
"merged_transcript_path": mergedPath,
@@ -173,22 +114,13 @@ func (polishStage) Run(ctx context.Context, env *Env, m *manifest.Manifest) (*St
"glossary_path": glossaryPath,
"run_output_path": finalProcessedPath,
"output_path": canonicalProcessedPath,
"run_report_path": finalReportPath,
"report_path": reportCanonicalPath,
"audita_work_dir": workDir,
"report_enabled": reportEnabled,
"modules": append([]string(nil), env.Config.Pipeline.Audita.Modules...),
"base_url": env.Config.Pipeline.Audita.BaseURL,
"model": env.Config.Pipeline.Audita.Model,
"modules": append(env.Config.Pipeline.Audita.Modules[:0:0], env.Config.Pipeline.Audita.Modules...),
"overlay": env.Config.Pipeline.Audita.Overlay,
"proposal_profile": env.Config.Pipeline.Audita.ProposalProfile,
"validation_profile": env.Config.Pipeline.Audita.ValidationProfile,
"transcript_description": env.Config.Pipeline.Audita.TranscriptDescription,
"config_path": env.Config.Pipeline.Audita.ConfigPath,
"output_schema": env.Config.Pipeline.Audita.OutputSchema,
"work_dir_retention": env.Config.Pipeline.Audita.WorkDirRetention,
"validation_model": env.Config.Pipeline.Audita.ValidationModel,
"total_llm_concurrency": totalLLMConcurrency,
"proposal_llm_concurrency": proposalLLMConcurrency,
"validation_llm_concurrency": validationConcurrency,
"llm_api_key": credentialReference,
"timeout": env.Config.Pipeline.Audita.Timeout,
"binary": env.Config.Pipeline.Audita.Binary,
"generated_config_path": generatedConfigPath,
@@ -198,22 +130,12 @@ func (polishStage) Run(ctx context.Context, env *Env, m *manifest.Manifest) (*St
"adapter_exit_code": res.ExitCode,
"adapter_invoked_binary": res.InvokedBinary,
"adapter_processed_output_path": res.ProcessedTranscriptPath,
"adapter_report_path": res.ReportPath,
"adapter_generated_config_path": res.GeneratedConfigPath,
"adapter_work_dir": res.WorkDir,
"adapter_stdout_log_path": res.StdoutLogPath,
"adapter_stderr_log_path": res.StderrLogPath,
"credential_env_var": credentialReference,
"credential_present": false,
}
if res.Metadata != nil {
meta["adapter_metadata"] = res.Metadata
if value, ok := res.Metadata["credential_present"]; ok {
meta["credential_present"] = value
}
if value, ok := res.Metadata["credential_env_var"]; ok {
meta["credential_env_var"] = value
}
}
return &StageResult{

69
internal/stage/polish_test.go
View File

@@ -8,6 +8,7 @@ import (
"testing"
"time"
configkit "gitea.maximumdirect.net/eric/ConfigKit"
"gitea.maximumdirect.net/eric/narratio/internal/adapters/audita"
"gitea.maximumdirect.net/eric/narratio/internal/artifacts"
"gitea.maximumdirect.net/eric/narratio/internal/config"
@@ -43,18 +44,12 @@ func TestPolishStagePolishesMergedTranscriptAndRecordsMetadata(t *testing.T) {
if req.GlossaryPath != filepath.Join(paths.InputsDir, "glossary.yml") {
t.Fatalf("glossary path = %q", req.GlossaryPath)
}
if req.WorkDir != filepath.Join(paths.ArtifactsDir, "audita-work") {
t.Fatalf("work dir = %q", req.WorkDir)
}
if len(result.Outputs) != 2 {
t.Fatalf("outputs len = %d, want 2", len(result.Outputs))
if len(result.Outputs) != 1 {
t.Fatalf("outputs len = %d, want 1", len(result.Outputs))
}
if result.Outputs[0].Kind != "transcript_polished" {
t.Fatalf("output[0] kind = %q, want transcript_polished", result.Outputs[0].Kind)
}
if result.Outputs[1].Kind != "audita_report" {
t.Fatalf("output[1] kind = %q, want audita_report", result.Outputs[1].Kind)
}
if len(result.Logs) != 2 {
t.Fatalf("logs = %#v, want 2", result.Logs)
}
@@ -65,18 +60,6 @@ func TestPolishStagePolishesMergedTranscriptAndRecordsMetadata(t *testing.T) {
if result.Metadata["stage"] != "polish" {
t.Fatalf("metadata stage = %#v, want polish", result.Metadata["stage"])
}
if result.Metadata["report_enabled"] != true {
t.Fatalf("metadata report_enabled = %#v, want true", result.Metadata["report_enabled"])
}
if result.Metadata["audita_work_dir"] != filepath.Join(paths.ArtifactsDir, "audita-work") {
t.Fatalf("metadata audita_work_dir = %#v", result.Metadata["audita_work_dir"])
}
if result.Metadata["total_llm_concurrency"] != 3 {
t.Fatalf("metadata total_llm_concurrency = %#v, want 3", result.Metadata["total_llm_concurrency"])
}
if result.Metadata["proposal_llm_concurrency"] != 2 {
t.Fatalf("metadata proposal_llm_concurrency = %#v, want 2", result.Metadata["proposal_llm_concurrency"])
}
if result.Metadata["output_schema"] != "audita-v1" {
t.Fatalf("metadata output_schema = %#v, want audita-v1", result.Metadata["output_schema"])
}
@@ -185,25 +168,6 @@ func TestPolishStageFailsWhenProcessedOutputInvalid(t *testing.T) {
}
}
func TestPolishStageFailsWhenReportInvalid(t *testing.T) {
env, m := setupPolishEnv(t)
paths := sessionPathsForEnv(env, m.SessionID)
writeFile(t, filepath.Join(paths.TranscriptsDir, "base.json"), `{"segments":[]}`)
setCurrentBuiltInEvidence(t, m, "merge", artifacts.TranscriptOutputKindBase, artifacts.ArtifactTranscriptBase, filepath.Join(paths.TranscriptsDir, "base.json"))
writeFile(t, filepath.Join(paths.InputsDir, "glossary.yml"), "terms: []\n")
badReport := filepath.Join(paths.ArtifactsDir, "bad.report.json")
writeFile(t, badReport, "not-json")
env.Audita = &audita.FakeRunner{Result: audita.PolishResult{ReportPath: badReport}}
_, err := (polishStage{}).Run(context.Background(), env, m)
if err == nil {
t.Fatal("expected error, got nil")
}
if !strings.Contains(err.Error(), "report") {
t.Fatalf("error = %q", err.Error())
}
}
func TestPolishStageUsesRunLocalPathsAndMaterializesCanonical(t *testing.T) {
env, m := setupPolishEnv(t)
env.Config.Session.Campaign = "sample-campaign"
@@ -244,32 +208,19 @@ func setupPolishEnv(t *testing.T) (*Env, *manifest.Manifest) {
writeFile(t, sessionPath, "session_id: 2026-05-03\n")
writeFile(t, pipelinePath, "workspace:\n root: "+workspace+"\n")
report := true
totalLLMConcurrency := 3
proposalLLMConcurrency := 2
validationLLMConcurrency := 2
cfg := &config.Config{
PipelinePath: pipelinePath,
SessionPath: sessionPath,
Pipeline: &config.PipelineConfig{
Workspace: config.WorkspaceConfig{Root: workspace},
Audita: config.AuditaConfig{
Binary: "audita",
Timeout: "3h",
LLMAPIKey: testSecretReference("AUDITA_LLM_API_KEY"),
Modules: []string{"glossary", "homophones", "grammar"},
BaseURL: "https://openrouter.ai/api/v1",
Model: "openrouter/google/gemma-4-31b-it",
TranscriptDescription: "Campaign Session 42",
ConfigPath: "/etc/audita/config.yml",
OutputSchema: "audita-v1",
WorkDirRetention: "auto",
ValidationModel: "openrouter/google/gemma-4-31b-it",
TotalLLMConcurrency: &totalLLMConcurrency,
ProposalLLMConcurrency: &proposalLLMConcurrency,
ValidationLLMConcurrency: &validationLLMConcurrency,
Report: &report,
Binary: "audita",
Timeout: "3h",
Credentials: []configkit.Secret{*testSecretReference("AUDITA_LLM_API_KEY")},
Modules: []string{"glossary", "homophones", "grammar"},
TranscriptDescription: "Campaign Session 42",
ConfigPath: "/etc/audita/config.yml",
OutputSchema: "audita-v1",
},
},
Session: &config.SessionConfig{

6
internal/stage/semantic_contracts_refinement.go
View File

@@ -18,9 +18,6 @@ const (
)
type polishSemanticConfig struct {
ServiceURL string `json:"service_url"`
Model string `json:"model"`
ValidationModel string `json:"validation_model"`
Modules []string `json:"modules"`
TranscriptDescription string `json:"transcript_description"`
OutputSchema string `json:"output_schema"`
@@ -74,9 +71,6 @@ func (polishStage) SemanticConfigFingerprint(env *Env) (manifest.SemanticConfigF
}
sort.Strings(modules)
return FingerprintSemanticConfig(polishSemanticConfigVersion, polishSemanticConfig{
ServiceURL: strings.TrimSpace(audita.BaseURL),
Model: strings.TrimSpace(audita.Model),
ValidationModel: strings.TrimSpace(audita.ValidationModel),
Modules: modules,
TranscriptDescription: strings.TrimSpace(audita.TranscriptDescription),
OutputSchema: strings.TrimSpace(audita.OutputSchema),

18
internal/stage/semantic_contracts_refinement_test.go
View File

@@ -3,6 +3,7 @@ package stage
import (
"testing"
configkit "gitea.maximumdirect.net/eric/ConfigKit"
"gitea.maximumdirect.net/eric/narratio/internal/config"
)
@@ -11,13 +12,10 @@ func TestPolishSemanticConfigSensitivity(t *testing.T) {
name string
mutate func(*Env)
}{
{name: "model", mutate: func(env *Env) { env.Config.Pipeline.Audita.Model = "production" }},
{name: "validation model", mutate: func(env *Env) { env.Config.Pipeline.Audita.ValidationModel = "validator-v2" }},
{name: "modules", mutate: func(env *Env) { env.Config.Pipeline.Audita.Modules = []string{"terms", "speakers", "style"} }},
{name: "description", mutate: func(env *Env) { env.Config.Pipeline.Audita.TranscriptDescription = "live campaign" }},
{name: "schema", mutate: func(env *Env) { env.Config.Pipeline.Audita.OutputSchema = "audita.transcript.v2" }},
{name: "external config", mutate: func(env *Env) { env.Config.Pipeline.Audita.ConfigPath = "configs/other.yml" }},
{name: "service", mutate: func(env *Env) { env.Config.Pipeline.Audita.BaseURL = "https://other.example" }},
}
assertRefinementChanges(t, polishStage{}, semantic)
assertRefinementUnchanged(t, polishStage{}, []struct {
@@ -28,12 +26,7 @@ func TestPolishSemanticConfigSensitivity(t *testing.T) {
{name: "runner settings", mutate: func(env *Env) {
env.Config.Pipeline.Audita.Binary = "/opt/audita"
env.Config.Pipeline.Audita.Timeout = "1h"
env.Config.Pipeline.Audita.TotalLLMConcurrency = intPointer(20)
env.Config.Pipeline.Audita.ProposalLLMConcurrency = intPointer(10)
env.Config.Pipeline.Audita.ValidationLLMConcurrency = intPointer(10)
env.Config.Pipeline.Audita.LLMAPIKey = testSecretReference("OTHER_KEY")
env.Config.Pipeline.Audita.WorkDirRetention = "always"
env.Config.Pipeline.Audita.Report = boolPointer(false)
env.Config.Pipeline.Audita.Credentials = []configkit.Secret{*testSecretReference("OTHER_KEY")}
}},
})
}
@@ -119,12 +112,9 @@ func refinementSemanticEnv() *Env {
env := initialSemanticEnv()
env.Config.Session.Title = "Session title"
env.Config.Pipeline.Audita = config.AuditaConfig{
Binary: "audita", Timeout: "10m", LLMAPIKey: testSecretReference("AUDITA_KEY"),
Modules: []string{"speakers", "terms"}, BaseURL: "https://audita.example",
Model: "testing", ValidationModel: "validator", TranscriptDescription: "tabletop session",
Binary: "audita", Timeout: "10m", Credentials: []configkit.Secret{*testSecretReference("AUDITA_KEY")},
Modules: []string{"speakers", "terms"}, TranscriptDescription: "tabletop session",
ConfigPath: "configs/audita.yml", OutputSchema: "audita.transcript.v1",
TotalLLMConcurrency: intPointer(4), ProposalLLMConcurrency: intPointer(2),
ValidationLLMConcurrency: intPointer(2), WorkDirRetention: "failure", Report: boolPointer(true),
}
env.Config.Pipeline.Normalize = &config.NormalizeConfig{
OutputPath: "transcripts/final.json", OutputSchema: "seriatim.transcript.v1", Report: boolPointer(true),