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

@@ -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)
}
}