Add output schema registry and public contract docs

This commit is contained in:
2026-05-13 12:59:10 +00:00
parent 9a77a0cd0b
commit 1bc5936681
21 changed files with 791 additions and 24 deletions

View File

@@ -15,6 +15,7 @@ const (
const (
DefaultModulesCSV = "glossary,homophones,glossary,spoken_word,grammar"
DefaultOutputSchema = "bare-segments"
DefaultPrimaryModel = "openrouter/google/gemma-4-31b-it"
DefaultPrimaryBaseURL = "https://openrouter.ai/api/v1"
DefaultPrimaryLLMTimeoutSeconds = 600
@@ -35,6 +36,7 @@ const (
type Config struct {
Modules []string
OutputSchema string
PrimaryLLM LLMConfig
ValidationLLM ValidationLLMConfig
TotalLLMConcurrency int
@@ -91,7 +93,8 @@ func Default() Config {
modules, _ := ParseModulesCSV(DefaultModulesCSV)
return Config{
Modules: modules,
Modules: modules,
OutputSchema: DefaultOutputSchema,
PrimaryLLM: LLMConfig{
Model: DefaultPrimaryModel,
BaseURL: DefaultPrimaryBaseURL,

View File

@@ -12,6 +12,9 @@ func TestDefaultConfigValues(t *testing.T) {
if got, want := strings.Join(cfg.Modules, ","), DefaultModulesCSV; got != want {
t.Fatalf("modules mismatch: got %q want %q", got, want)
}
if cfg.OutputSchema != DefaultOutputSchema {
t.Fatalf("unexpected default output schema: %q", cfg.OutputSchema)
}
if cfg.PrimaryLLM.Model != DefaultPrimaryModel {
t.Fatalf("unexpected default primary model: %q", cfg.PrimaryLLM.Model)
}
@@ -186,12 +189,14 @@ func TestApplyCLIOverridesPrecedence(t *testing.T) {
model := "cli-model"
workDir := "/cli/work"
modules := "grammar"
outputSchema := "audita-v1"
totalLLMConcurrency := 5
proposalLLMConcurrency := 3
overrides := CLIOverrides{
PrimaryModel: &model,
WorkDir: &workDir,
ModulesCSV: &modules,
OutputSchema: &outputSchema,
TotalLLMConcurrency: &totalLLMConcurrency,
ProposalLLMConcurrency: &proposalLLMConcurrency,
}
@@ -209,6 +214,9 @@ func TestApplyCLIOverridesPrecedence(t *testing.T) {
if !reflect.DeepEqual(cfg.Modules, []string{"grammar"}) {
t.Fatalf("unexpected modules: %#v", cfg.Modules)
}
if cfg.OutputSchema != "audita-v1" {
t.Fatalf("expected CLI output schema override, got %q", cfg.OutputSchema)
}
if cfg.TotalLLMConcurrency != 5 {
t.Fatalf("expected CLI total concurrency override, got %d", cfg.TotalLLMConcurrency)
}
@@ -275,6 +283,7 @@ func TestApplyCLIOverridesCanonicalTotalWinsLegacyAlias(t *testing.T) {
func TestValidationFailures(t *testing.T) {
cfg := Default()
cfg.OutputSchema = "unknown-schema"
cfg.PrimaryLLM.TimeoutSeconds = -1
cfg.TotalLLMConcurrency = 0
cfg.ProposalLLMConcurrency = 0
@@ -301,6 +310,7 @@ func TestValidationFailures(t *testing.T) {
"min section tokens",
"grammar confidence threshold",
"work dir retention",
"unsupported output schema",
} {
if !strings.Contains(message, expected) {
t.Fatalf("expected error to contain %q, got %q", expected, message)

View File

@@ -16,32 +16,37 @@ const SupportedFileConfigVersion = 1
var envVarNamePattern = regexp.MustCompile(`^[A-Za-z_][A-Za-z0-9_]*$`)
type FileConfig struct {
Version int `yaml:"version"`
Pipeline *FileConfigPipeline `yaml:"pipeline,omitempty"`
LLM *FileConfigLLM `yaml:"llm,omitempty"`
Concurrency *FileConfigConcurrency `yaml:"concurrency,omitempty"`
Chunking *FileConfigChunking `yaml:"chunking,omitempty"`
Normalization *FileConfigNormalization `yaml:"normalization,omitempty"`
Thresholds *FileConfigThresholds `yaml:"thresholds,omitempty"`
Context *FileConfigContext `yaml:"context,omitempty"`
Diagnostics *FileConfigDiagnostics `yaml:"diagnostics,omitempty"`
Version int `yaml:"version"`
Pipeline *FileConfigPipeline `yaml:"pipeline,omitempty"`
Output *FileConfigOutput `yaml:"output,omitempty"`
LLM *FileConfigLLM `yaml:"llm,omitempty"`
Concurrency *FileConfigConcurrency `yaml:"concurrency,omitempty"`
Chunking *FileConfigChunking `yaml:"chunking,omitempty"`
Normalization *FileConfigNormalization `yaml:"normalization,omitempty"`
Thresholds *FileConfigThresholds `yaml:"thresholds,omitempty"`
Context *FileConfigContext `yaml:"context,omitempty"`
Diagnostics *FileConfigDiagnostics `yaml:"diagnostics,omitempty"`
}
type FileConfigPipeline struct {
Modules []string `yaml:"modules,omitempty"`
}
type FileConfigOutput struct {
Schema *string `yaml:"schema,omitempty"`
}
type FileConfigLLM struct {
Proposal *FileConfigLLMTarget `yaml:"proposal,omitempty"`
Validation *FileConfigLLMTarget `yaml:"validation,omitempty"`
}
type FileConfigLLMTarget struct {
BaseURL *string `yaml:"base_url,omitempty"`
Model *string `yaml:"model,omitempty"`
APIKeyEnv *string `yaml:"api_key_env,omitempty"`
Timeout *fileConfigDurationOrInt `yaml:"timeout,omitempty"`
MaxRetries *int `yaml:"max_retries,omitempty"`
BaseURL *string `yaml:"base_url,omitempty"`
Model *string `yaml:"model,omitempty"`
APIKeyEnv *string `yaml:"api_key_env,omitempty"`
Timeout *fileConfigDurationOrInt `yaml:"timeout,omitempty"`
MaxRetries *int `yaml:"max_retries,omitempty"`
}
type FileConfigConcurrency struct {
@@ -194,6 +199,9 @@ func (c *Config) applyFileConfigWithLookup(fileCfg FileConfig, lookup func(strin
if fileCfg.Pipeline != nil && len(fileCfg.Pipeline.Modules) > 0 {
c.Modules = append([]string(nil), fileCfg.Pipeline.Modules...)
}
if fileCfg.Output != nil && fileCfg.Output.Schema != nil {
c.OutputSchema = strings.TrimSpace(*fileCfg.Output.Schema)
}
if fileCfg.LLM != nil {
if fileCfg.LLM.Proposal != nil {

View File

@@ -11,6 +11,8 @@ func TestParseFileConfigYAMLValid(t *testing.T) {
version: 1
pipeline:
modules: [glossary, homophones, grammar]
output:
schema: audita-v1
llm:
proposal:
base_url: https://example.test/v1
@@ -58,6 +60,9 @@ diagnostics:
if cfg.Pipeline == nil || len(cfg.Pipeline.Modules) != 3 {
t.Fatalf("unexpected pipeline modules: %#v", cfg.Pipeline)
}
if cfg.Output == nil || cfg.Output.Schema == nil || *cfg.Output.Schema != "audita-v1" {
t.Fatalf("expected output schema audita-v1, got %#v", cfg.Output)
}
if cfg.LLM == nil || cfg.LLM.Proposal == nil || cfg.LLM.Validation == nil {
t.Fatalf("expected llm proposal+validation blocks")
}
@@ -78,13 +83,13 @@ version: 1
pipeline:
modules: [grammar]
output:
schema: v1
unknown: v1
`
_, err := ParseFileConfigYAML([]byte(raw))
if err == nil {
t.Fatalf("expected unknown field error")
}
if !strings.Contains(err.Error(), "field output not found") {
if !strings.Contains(err.Error(), "field unknown not found") {
t.Fatalf("unexpected error: %v", err)
}
}
@@ -116,6 +121,8 @@ func TestApplyFileConfigParsesAndMergesFields(t *testing.T) {
version: 1
pipeline:
modules: [spoken_word, grammar]
output:
schema: audita-v1
llm:
proposal:
model: provider/new-proposal
@@ -164,6 +171,9 @@ diagnostics:
if strings.Join(cfg.Modules, ",") != "spoken_word,grammar" {
t.Fatalf("unexpected modules: %#v", cfg.Modules)
}
if cfg.OutputSchema != "audita-v1" {
t.Fatalf("unexpected output schema: %q", cfg.OutputSchema)
}
if cfg.PrimaryLLM.Model != "provider/new-proposal" {
t.Fatalf("unexpected proposal model: %q", cfg.PrimaryLLM.Model)
}

View File

@@ -7,6 +7,7 @@ import (
type CLIOverrides struct {
ModulesCSV *string
OutputSchema *string
PrimaryLLMAPIKey *string
ValidationLLMAPIKey *string
PrimaryModel *string
@@ -46,6 +47,9 @@ func (c *Config) ApplyCLIOverrides(overrides CLIOverrides) error {
}
c.Modules = modules
}
if overrides.OutputSchema != nil {
c.OutputSchema = strings.TrimSpace(*overrides.OutputSchema)
}
if overrides.PrimaryLLMAPIKey != nil {
c.PrimaryLLM.APIKey = *overrides.PrimaryLLMAPIKey

View File

@@ -17,6 +17,15 @@ func (c Config) Validate() error {
break
}
}
if strings.TrimSpace(c.OutputSchema) == "" {
issues = append(issues, "output schema must not be empty")
} else {
switch strings.TrimSpace(c.OutputSchema) {
case "bare-segments", "audita-v1":
default:
issues = append(issues, fmt.Sprintf("unsupported output schema %q", c.OutputSchema))
}
}
if c.PrimaryLLM.TimeoutSeconds <= 0 {
issues = append(issues, "primary llm timeout seconds must be greater than zero")

View File

@@ -55,6 +55,7 @@ type InvocationMetadata struct {
ReportJSONPath string `json:"report_json_path,omitempty"`
ConfigPath string `json:"config_path,omitempty"`
ConfigSource string `json:"config_source,omitempty"`
ConfigVersion *int `json:"config_version,omitempty"`
TranscriptDescription string `json:"transcript_description,omitempty"`
Modules []string `json:"modules"`
RunID string `json:"run_id"`

View File

@@ -0,0 +1,72 @@
package outputschema
import (
"encoding/json"
"fmt"
"strings"
"gitea.maximumdirect.net/eric/audita/internal/core/schema"
)
const (
SchemaBareSegments = "bare-segments"
SchemaAuditaV1 = "audita-v1"
)
type Encoder func(*schema.Transcript) ([]byte, error)
type Definition struct {
Key string
Encoder Encoder
}
var definitions = map[string]Definition{
SchemaBareSegments: {
Key: SchemaBareSegments,
Encoder: schema.TranscriptToJSON,
},
SchemaAuditaV1: {
Key: SchemaAuditaV1,
Encoder: encodeAuditaV1,
},
}
func Resolve(key string) (Definition, error) {
normalized := strings.TrimSpace(key)
if normalized == "" {
return Definition{}, fmt.Errorf("output schema must not be empty")
}
def, ok := definitions[normalized]
if !ok {
return Definition{}, fmt.Errorf("unsupported output schema %q", normalized)
}
return def, nil
}
func encodeAuditaV1(transcript *schema.Transcript) ([]byte, error) {
if transcript == nil {
transcript = &schema.Transcript{}
}
payload := map[string]any{
"schema": "audita-v1",
"version": "v1",
"segments": func() []map[string]any {
out := make([]map[string]any, len(transcript.Segments))
for i, s := range transcript.Segments {
item := map[string]any{
"id": s.ID,
"speaker": s.Speaker,
"start": s.Start,
"end": s.End,
"text": s.Text,
}
if len(s.Categories) > 0 {
item["categories"] = s.Categories
}
out[i] = item
}
return out
}(),
}
return json.MarshalIndent(payload, "", " ")
}

View File

@@ -0,0 +1,58 @@
package outputschema
import (
"encoding/json"
"strings"
"testing"
"gitea.maximumdirect.net/eric/audita/internal/core/schema"
)
func tinyTranscript() *schema.Transcript {
return &schema.Transcript{Segments: []schema.Segment{
{ID: 1, Speaker: "A", Start: 0, End: 1, Text: "hello"},
}}
}
func TestResolveBareSegments(t *testing.T) {
def, err := Resolve(SchemaBareSegments)
if err != nil {
t.Fatalf("Resolve error: %v", err)
}
raw, err := def.Encoder(tinyTranscript())
if err != nil {
t.Fatalf("encode error: %v", err)
}
if !strings.HasPrefix(strings.TrimSpace(string(raw)), "[") {
t.Fatalf("expected bare-segments array output, got %s", string(raw))
}
}
func TestResolveAuditaV1(t *testing.T) {
def, err := Resolve(SchemaAuditaV1)
if err != nil {
t.Fatalf("Resolve error: %v", err)
}
raw, err := def.Encoder(tinyTranscript())
if err != nil {
t.Fatalf("encode error: %v", err)
}
var out struct {
Schema string `json:"schema"`
Version string `json:"version"`
Segments []map[string]any `json:"segments"`
}
if err := json.Unmarshal(raw, &out); err != nil {
t.Fatalf("unmarshal error: %v", err)
}
if out.Schema != "audita-v1" || out.Version != "v1" || len(out.Segments) != 1 {
t.Fatalf("unexpected audita-v1 output: %+v", out)
}
}
func TestResolveUnknown(t *testing.T) {
_, err := Resolve("seriatim-intermediate")
if err == nil || !strings.Contains(err.Error(), "unsupported output schema") {
t.Fatalf("expected unsupported output schema error, got %v", err)
}
}

View File

@@ -10,6 +10,7 @@ import (
)
type ProcessReport struct {
ReportMetadata ReportMetadata `json:"report_metadata"`
Phase string `json:"phase"`
Status string `json:"status"`
Operation string `json:"operation"`
@@ -32,6 +33,18 @@ type ProcessReport struct {
ModuleResults []ModuleReport `json:"module_results,omitempty"`
}
const (
DefaultProcessReportSchemaName = "audita-process-report"
DefaultProcessReportSchemaVersion = "v1"
)
type ReportMetadata struct {
ReportSchemaName string `json:"report_schema_name"`
ReportSchemaVersion string `json:"report_schema_version"`
OutputSchema string `json:"output_schema"`
ConfigVersion *int `json:"config_version,omitempty"`
}
type ModuleReport struct {
ModuleKey string `json:"module_key"`
ModuleInstance string `json:"module_instance"`

View File

@@ -11,6 +11,11 @@ import (
func TestProcessReportModuleResultsJSONSuccessAndSkipped(t *testing.T) {
now := time.Now().UTC()
report := ProcessReport{
ReportMetadata: ReportMetadata{
ReportSchemaName: DefaultProcessReportSchemaName,
ReportSchemaVersion: DefaultProcessReportSchemaVersion,
OutputSchema: "bare-segments",
},
Phase: "default_pipeline",
Status: "success",
ModuleResults: []ModuleReport{
@@ -75,11 +80,21 @@ func TestProcessReportModuleResultsJSONSuccessAndSkipped(t *testing.T) {
if parsed.ModulesSummary == nil || parsed.ModulesSummary.TotalSkippedChanges != 1 {
t.Fatalf("unexpected module summary: %+v", parsed.ModulesSummary)
}
if parsed.ReportMetadata.ReportSchemaName != DefaultProcessReportSchemaName ||
parsed.ReportMetadata.ReportSchemaVersion != DefaultProcessReportSchemaVersion ||
parsed.ReportMetadata.OutputSchema != "bare-segments" {
t.Fatalf("unexpected report metadata after roundtrip: %+v", parsed.ReportMetadata)
}
}
func TestProcessReportModuleResultsJSONFailedModule(t *testing.T) {
now := time.Now().UTC()
report := ProcessReport{
ReportMetadata: ReportMetadata{
ReportSchemaName: DefaultProcessReportSchemaName,
ReportSchemaVersion: DefaultProcessReportSchemaVersion,
OutputSchema: "audita-v1",
},
Phase: "default_pipeline",
Status: "failed",
ModuleResults: []ModuleReport{
@@ -106,6 +121,9 @@ func TestProcessReportModuleResultsJSONFailedModule(t *testing.T) {
if _, ok := decoded["module_results"]; !ok {
t.Fatalf("expected module_results field")
}
if _, ok := decoded["report_metadata"]; !ok {
t.Fatalf("expected report_metadata field")
}
if _, ok := decoded["modules_summary"]; !ok {
t.Fatalf("expected modules_summary field")
}