Add artifact reading and output validation

This commit is contained in:
2026-07-28 04:23:50 +00:00
parent ebc1f3e919
commit 62b26fb29e
10 changed files with 1116 additions and 7 deletions

View File

@@ -0,0 +1,292 @@
package validate
import (
"context"
"encoding/json"
"errors"
"fmt"
"io/fs"
"os"
"path"
"path/filepath"
"strings"
"gitea.maximumdirect.net/eric/promptkit/internal/domain"
"gitea.maximumdirect.net/eric/promptkit/internal/filecatalog"
"github.com/santhosh-tekuri/jsonschema/v6"
)
// StandardValidator provides basic, JSON, and JSON Schema output validation.
type StandardValidator struct {
schemaBaseDir string
}
type FSValidator struct {
fsys fs.FS
root string
}
func NewStandardValidator(schemaBaseDir string) Validator {
return &StandardValidator{schemaBaseDir: schemaBaseDir}
}
func NewFSValidator(fsys fs.FS, root string) Validator {
return &FSValidator{fsys: fsys, root: root}
}
func (v *StandardValidator) Validate(ctx context.Context, artifact *domain.Artifact, contract domain.OutputContract) (domain.ValidationResult, error) {
return validateArtifact(ctx, artifact, contract, v.validateJSONSchema)
}
func (v *FSValidator) Validate(ctx context.Context, artifact *domain.Artifact, contract domain.OutputContract) (domain.ValidationResult, error) {
return validateArtifact(ctx, artifact, contract, v.validateJSONSchema)
}
type schemaValidatorFunc func(instance any, schemaPath string) ([]string, error)
func validateArtifact(ctx context.Context, artifact *domain.Artifact, contract domain.OutputContract, validateSchema schemaValidatorFunc) (domain.ValidationResult, error) {
select {
case <-ctx.Done():
return domain.ValidationResult{}, ctx.Err()
default:
}
res := domain.ValidationResult{
Mode: contract.ValidationMode,
SchemaPath: contract.SchemaPath,
RepairAttempts: contract.RepairAttempts,
}
if artifact == nil {
return domain.ValidationResult{}, errors.New("artifact is required for validation")
}
switch contract.ValidationMode {
case domain.ValidationNone:
res.Status = domain.ValidationSkipped
res.IsValid = true
return res, nil
case domain.ValidationBasic:
if strings.TrimSpace(string(artifact.Body)) == "" {
res.Status = domain.ValidationFailed
res.IsValid = false
res.Errors = []string{"output is empty"}
return res, nil
}
res.Status = domain.ValidationPassed
res.IsValid = true
return res, nil
case domain.ValidationJSON:
_, jsonErr := parseJSON(artifact.Body)
if jsonErr != nil {
res.Status = domain.ValidationFailed
res.IsValid = false
res.Errors = []string{fmt.Sprintf("invalid JSON: %v", jsonErr)}
return res, nil
}
res.Status = domain.ValidationPassed
res.IsValid = true
return res, nil
case domain.ValidationJSONSchema:
instance, jsonErr := parseJSON(artifact.Body)
if jsonErr != nil {
res.Status = domain.ValidationFailed
res.IsValid = false
res.Errors = []string{fmt.Sprintf("invalid JSON: %v", jsonErr)}
return res, nil
}
validationErrors, err := validateSchema(instance, contract.SchemaPath)
if err != nil {
return domain.ValidationResult{}, err
}
if len(validationErrors) > 0 {
res.Status = domain.ValidationFailed
res.IsValid = false
res.Errors = validationErrors
return res, nil
}
res.Status = domain.ValidationPassed
res.IsValid = true
return res, nil
default:
return domain.ValidationResult{}, fmt.Errorf("unsupported validation mode: %q", contract.ValidationMode)
}
}
func (v *StandardValidator) validateJSONSchema(instance any, schemaPath string) ([]string, error) {
resolvedSchemaPath, err := v.resolveSchemaPath(schemaPath)
if err != nil {
return nil, err
}
compiler := jsonschema.NewCompiler()
schema, err := compiler.Compile(resolvedSchemaPath)
if err != nil {
return nil, fmt.Errorf("failed to compile JSON schema %q: %w", resolvedSchemaPath, err)
}
if err := schema.Validate(instance); err != nil {
return []string{fmt.Sprintf("json schema validation failed: %v", err)}, nil
}
return nil, nil
}
func (v *FSValidator) validateJSONSchema(instance any, schemaPath string) ([]string, error) {
schemaName, schemaDoc, err := v.loadSchemaDocument(schemaPath)
if err != nil {
return nil, err
}
resourceURL := fsSchemaResourceURL(schemaName)
compiler := jsonschema.NewCompiler()
if err := compiler.AddResource(resourceURL, schemaDoc); err != nil {
return nil, fmt.Errorf("failed to register JSON schema %q: %w", schemaName, err)
}
schema, err := compiler.Compile(resourceURL)
if err != nil {
return nil, fmt.Errorf("failed to compile JSON schema %q: %w", schemaName, err)
}
if err := schema.Validate(instance); err != nil {
return []string{fmt.Sprintf("json schema validation failed: %v", err)}, nil
}
return nil, nil
}
func parseJSON(body []byte) (any, error) {
var v any
if err := json.Unmarshal(body, &v); err != nil {
return nil, err
}
return v, nil
}
func (v *StandardValidator) LoadSchemaDocument(ctx context.Context, schemaPath string) (any, error) {
select {
case <-ctx.Done():
return nil, ctx.Err()
default:
}
resolved, err := v.resolveSchemaPath(schemaPath)
if err != nil {
return nil, err
}
raw, err := os.ReadFile(resolved)
if err != nil {
return nil, fmt.Errorf("failed to read schema file %q: %w", resolved, err)
}
var doc any
if err := json.Unmarshal(raw, &doc); err != nil {
return nil, fmt.Errorf("failed to decode JSON schema %q: %w", resolved, err)
}
return doc, nil
}
func (v *FSValidator) LoadSchemaDocument(ctx context.Context, schemaPath string) (any, error) {
select {
case <-ctx.Done():
return nil, ctx.Err()
default:
}
_, doc, err := v.loadSchemaDocument(schemaPath)
if err != nil {
return nil, err
}
return doc, nil
}
func (v *StandardValidator) resolveSchemaPath(schemaPath string) (string, error) {
if strings.TrimSpace(schemaPath) == "" {
return "", errors.New("schema path is required for json_schema validation")
}
resolved := schemaPath
if !filepath.IsAbs(schemaPath) {
resolved = filepath.Join(v.schemaBaseDir, schemaPath)
}
resolved = filepath.Clean(resolved)
if _, err := os.Stat(resolved); err != nil {
return "", fmt.Errorf("failed to access schema file %q: %w", resolved, err)
}
return resolved, nil
}
func (v *FSValidator) loadSchemaDocument(schemaPath string) (string, any, error) {
resolved, err := v.resolveSchemaPath(schemaPath)
if err != nil {
return "", nil, err
}
raw, err := fs.ReadFile(v.fsys, resolved)
if err != nil {
return "", nil, fmt.Errorf("failed to read schema file %q: %w", resolved, err)
}
var doc any
if err := json.Unmarshal(raw, &doc); err != nil {
return "", nil, fmt.Errorf("failed to decode JSON schema %q: %w", resolved, err)
}
return resolved, doc, nil
}
func (v *FSValidator) resolveSchemaPath(schemaPath string) (string, error) {
if strings.TrimSpace(schemaPath) == "" {
return "", errors.New("schema path is required for json_schema validation")
}
if v.fsys == nil {
return "", errors.New("schema filesystem is nil")
}
cleanRoot := filecatalog.CleanFSRoot(v.root)
rootInfo, err := fs.Stat(v.fsys, cleanRoot)
if err != nil {
return "", fmt.Errorf("failed to access schema source %q: %w", cleanRoot, err)
}
var resolved string
if rootInfo.IsDir() {
resolvedPath, _, err := filecatalog.ResolveFSPath(cleanRoot, cleanRoot, schemaPath)
if err != nil {
return "", err
}
resolved = resolvedPath
} else {
cleanSchemaPath, err := cleanSchemaFSPath(schemaPath)
if err != nil {
return "", err
}
if cleanSchemaPath != path.Base(cleanRoot) {
return "", fmt.Errorf("schema path %q does not match schema file %q", cleanSchemaPath, path.Base(cleanRoot))
}
resolved = cleanRoot
}
if _, err := fs.Stat(v.fsys, resolved); err != nil {
return "", fmt.Errorf("failed to access schema file %q: %w", resolved, err)
}
return resolved, nil
}
func cleanSchemaFSPath(schemaPath string) (string, error) {
cleaned := strings.TrimSpace(schemaPath)
if cleaned == "" {
return "", errors.New("schema path is required for json_schema validation")
}
cleaned = path.Clean(cleaned)
if path.IsAbs(cleaned) {
return "", fmt.Errorf("schema path %q must be relative", schemaPath)
}
return cleaned, nil
}
func fsSchemaResourceURL(schemaName string) string {
return "promptkit-schema:///" + strings.TrimPrefix(path.Clean(schemaName), "/")
}

View File

@@ -0,0 +1,413 @@
package validate
import (
"context"
"os"
"path/filepath"
"strings"
"testing"
"testing/fstest"
"gitea.maximumdirect.net/eric/promptkit/internal/domain"
)
func TestStandardValidatorNoneSkipped(t *testing.T) {
v := NewStandardValidator("")
res, err := v.Validate(context.Background(), &domain.Artifact{Body: []byte("ignored")}, domain.OutputContract{
ValidationMode: domain.ValidationNone,
})
if err != nil {
t.Fatalf("expected no error, got %v", err)
}
if res.Status != domain.ValidationSkipped {
t.Fatalf("expected skipped, got %q", res.Status)
}
if !res.IsValid {
t.Fatal("expected valid=true for skipped")
}
}
func TestStandardValidatorBasicSuccess(t *testing.T) {
v := NewStandardValidator("")
res, err := v.Validate(context.Background(), &domain.Artifact{Body: []byte("hello")}, domain.OutputContract{
ValidationMode: domain.ValidationBasic,
})
if err != nil {
t.Fatalf("expected no error, got %v", err)
}
if res.Status != domain.ValidationPassed || !res.IsValid {
t.Fatalf("expected passed/valid, got status=%q valid=%v", res.Status, res.IsValid)
}
}
func TestStandardValidatorBasicFailureEmpty(t *testing.T) {
v := NewStandardValidator("")
res, err := v.Validate(context.Background(), &domain.Artifact{Body: []byte(" \n\t ")}, domain.OutputContract{
ValidationMode: domain.ValidationBasic,
})
if err != nil {
t.Fatalf("expected no error, got %v", err)
}
if res.Status != domain.ValidationFailed || res.IsValid {
t.Fatalf("expected failed/invalid, got status=%q valid=%v", res.Status, res.IsValid)
}
if len(res.Errors) == 0 {
t.Fatal("expected validation errors")
}
}
func TestStandardValidatorJSONSuccess(t *testing.T) {
v := NewStandardValidator("")
res, err := v.Validate(context.Background(), &domain.Artifact{Body: []byte(`{"ok":true}`)}, domain.OutputContract{
ValidationMode: domain.ValidationJSON,
})
if err != nil {
t.Fatalf("expected no error, got %v", err)
}
if res.Status != domain.ValidationPassed || !res.IsValid {
t.Fatalf("expected passed/valid, got status=%q valid=%v", res.Status, res.IsValid)
}
}
func TestStandardValidatorJSONFailure(t *testing.T) {
v := NewStandardValidator("")
res, err := v.Validate(context.Background(), &domain.Artifact{Body: []byte(`{"ok":`)}, domain.OutputContract{
ValidationMode: domain.ValidationJSON,
})
if err != nil {
t.Fatalf("expected no error, got %v", err)
}
if res.Status != domain.ValidationFailed || res.IsValid {
t.Fatalf("expected failed/invalid, got status=%q valid=%v", res.Status, res.IsValid)
}
if len(res.Errors) == 0 {
t.Fatal("expected parse errors")
}
}
func TestStandardValidatorJSONSchemaSuccess(t *testing.T) {
tmp := t.TempDir()
schemaPath := filepath.Join(tmp, "schema.json")
if err := os.WriteFile(schemaPath, []byte(`{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"type": "object",
"required": ["name"],
"properties": {
"name": {"type": "string"}
}
}`), 0644); err != nil {
t.Fatal(err)
}
v := NewStandardValidator(tmp)
res, err := v.Validate(context.Background(), &domain.Artifact{Body: []byte(`{"name":"eris"}`)}, domain.OutputContract{
ValidationMode: domain.ValidationJSONSchema,
SchemaPath: "schema.json",
})
if err != nil {
t.Fatalf("expected no error, got %v", err)
}
if res.Status != domain.ValidationPassed || !res.IsValid {
t.Fatalf("expected passed/valid, got status=%q valid=%v", res.Status, res.IsValid)
}
}
func TestStandardValidatorJSONSchemaNestedSchemaPathSuccess(t *testing.T) {
tmp := t.TempDir()
nestedDir := filepath.Join(tmp, "dnd")
if err := os.MkdirAll(nestedDir, 0o755); err != nil {
t.Fatal(err)
}
if err := os.WriteFile(filepath.Join(nestedDir, "schema.json"), []byte(`{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"type": "object",
"required": ["name"],
"properties": {
"name": {"type": "string"}
}
}`), 0644); err != nil {
t.Fatal(err)
}
v := NewStandardValidator(tmp)
res, err := v.Validate(context.Background(), &domain.Artifact{Body: []byte(`{"name":"eris"}`)}, domain.OutputContract{
ValidationMode: domain.ValidationJSONSchema,
SchemaPath: filepath.Join("dnd", "schema.json"),
})
if err != nil {
t.Fatalf("expected no error, got %v", err)
}
if res.Status != domain.ValidationPassed || !res.IsValid {
t.Fatalf("expected passed/valid, got status=%q valid=%v", res.Status, res.IsValid)
}
}
func TestStandardValidatorJSONSchemaNestedSchemaPathMissing(t *testing.T) {
v := NewStandardValidator(t.TempDir())
_, err := v.Validate(context.Background(), &domain.Artifact{Body: []byte(`{"name":"eris"}`)}, domain.OutputContract{
ValidationMode: domain.ValidationJSONSchema,
SchemaPath: filepath.Join("dnd", "missing.json"),
})
if err == nil {
t.Fatal("expected nested schema load error")
}
}
func TestStandardValidatorJSONSchemaFailure(t *testing.T) {
tmp := t.TempDir()
schemaPath := filepath.Join(tmp, "schema.json")
if err := os.WriteFile(schemaPath, []byte(`{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"type": "object",
"required": ["name"],
"properties": {
"name": {"type": "string"}
}
}`), 0644); err != nil {
t.Fatal(err)
}
v := NewStandardValidator(tmp)
res, err := v.Validate(context.Background(), &domain.Artifact{Body: []byte(`{"count":1}`)}, domain.OutputContract{
ValidationMode: domain.ValidationJSONSchema,
SchemaPath: "schema.json",
})
if err != nil {
t.Fatalf("expected no error, got %v", err)
}
if res.Status != domain.ValidationFailed || res.IsValid {
t.Fatalf("expected failed/invalid, got status=%q valid=%v", res.Status, res.IsValid)
}
if len(res.Errors) == 0 {
t.Fatal("expected schema errors")
}
}
func TestStandardValidatorJSONSchemaSchemaLoadError(t *testing.T) {
v := NewStandardValidator(t.TempDir())
_, err := v.Validate(context.Background(), &domain.Artifact{Body: []byte(`{"name":"eris"}`)}, domain.OutputContract{
ValidationMode: domain.ValidationJSONSchema,
SchemaPath: "missing.json",
})
if err == nil {
t.Fatal("expected schema load error")
}
}
func TestStandardValidatorJSONSchemaCompilationError(t *testing.T) {
tmp := t.TempDir()
if err := os.WriteFile(filepath.Join(tmp, "schema.json"), []byte(`{"type":42}`), 0o644); err != nil {
t.Fatal(err)
}
v := NewStandardValidator(tmp)
res, err := v.Validate(context.Background(), &domain.Artifact{Body: []byte(`{}`)}, domain.OutputContract{
ValidationMode: domain.ValidationJSONSchema,
SchemaPath: "schema.json",
})
if err == nil || !strings.Contains(err.Error(), "failed to compile JSON schema") {
t.Fatalf("expected schema compilation error, got result=%#v error=%v", res, err)
}
}
func TestStandardValidatorLoadSchemaDocumentSuccess(t *testing.T) {
tmp := t.TempDir()
if err := os.WriteFile(filepath.Join(tmp, "schema.json"), []byte(`{
"type": "object",
"properties": {
"name": {"type": "string"}
}
}`), 0644); err != nil {
t.Fatal(err)
}
v := NewStandardValidator(tmp)
loader, ok := v.(SchemaDocumentLoader)
if !ok {
t.Fatal("standard validator must implement SchemaDocumentLoader")
}
doc, err := loader.LoadSchemaDocument(context.Background(), "schema.json")
if err != nil {
t.Fatalf("expected no error, got %v", err)
}
obj, ok := doc.(map[string]any)
if !ok {
t.Fatalf("expected object document, got %#v", doc)
}
if obj["type"] != "object" {
t.Fatalf("expected schema type=object, got %#v", obj["type"])
}
}
func TestStandardValidatorLoadSchemaDocumentInvalidJSON(t *testing.T) {
tmp := t.TempDir()
if err := os.WriteFile(filepath.Join(tmp, "schema.json"), []byte(`{`), 0644); err != nil {
t.Fatal(err)
}
v := NewStandardValidator(tmp)
loader, ok := v.(SchemaDocumentLoader)
if !ok {
t.Fatal("standard validator must implement SchemaDocumentLoader")
}
_, err := loader.LoadSchemaDocument(context.Background(), "schema.json")
if err == nil {
t.Fatal("expected decode error")
}
}
func TestFSValidatorJSONSchemaSuccess(t *testing.T) {
v := NewFSValidator(fstest.MapFS{
"schemas/events.schema.json": &fstest.MapFile{Data: []byte(`{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"type": "object",
"required": ["events"],
"properties": {
"events": {"type": "array"}
}
}`)},
}, "schemas")
res, err := v.Validate(context.Background(), &domain.Artifact{Body: []byte(`{"events":[]}`)}, domain.OutputContract{
ValidationMode: domain.ValidationJSONSchema,
SchemaPath: "events.schema.json",
})
if err != nil {
t.Fatalf("expected no error, got %v", err)
}
if res.Status != domain.ValidationPassed || !res.IsValid {
t.Fatalf("expected passed/valid, got status=%q valid=%v", res.Status, res.IsValid)
}
}
func TestFSValidatorJSONSchemaRegistrationError(t *testing.T) {
v := NewFSValidator(fstest.MapFS{
"schemas/%zz.json": &fstest.MapFile{Data: []byte(`{"type":"object"}`)},
}, "schemas")
res, err := v.Validate(context.Background(), &domain.Artifact{Body: []byte(`{}`)}, domain.OutputContract{
ValidationMode: domain.ValidationJSONSchema,
SchemaPath: "%zz.json",
})
if err == nil || !strings.Contains(err.Error(), "failed to register JSON schema") {
t.Fatalf("expected schema registration error, got result=%#v error=%v", res, err)
}
}
func TestFSValidatorJSONSchemaPathContainment(t *testing.T) {
t.Run("nested schema inside root succeeds", func(t *testing.T) {
v := NewFSValidator(fstest.MapFS{
"schemas/nested/events.schema.json": &fstest.MapFile{Data: []byte(`{
"type": "object",
"required": ["events"],
"properties": {
"events": {"type": "array"}
}
}`)},
}, "schemas")
res, err := v.Validate(context.Background(), &domain.Artifact{Body: []byte(`{"events":[]}`)}, domain.OutputContract{
ValidationMode: domain.ValidationJSONSchema,
SchemaPath: "nested/events.schema.json",
})
if err != nil {
t.Fatalf("expected no error, got %v", err)
}
if res.Status != domain.ValidationPassed || !res.IsValid {
t.Fatalf("expected passed/valid, got status=%q valid=%v", res.Status, res.IsValid)
}
})
tests := []struct {
name string
schemaPath string
wantErr string
}{
{name: "parent escape rejected", schemaPath: "../outside.schema.json", wantErr: "escapes source root"},
{name: "absolute path rejected", schemaPath: "/outside.schema.json", wantErr: "must be relative"},
}
for _, tc := range tests {
t.Run(tc.name, func(t *testing.T) {
v := NewFSValidator(fstest.MapFS{
"schemas/events.schema.json": &fstest.MapFile{Data: []byte(`{"type":"object"}`)},
"outside.schema.json": &fstest.MapFile{Data: []byte(`{"type":"object"}`)},
"schemas/outside.schema.json": &fstest.MapFile{Data: []byte(`{"type":"object"}`)},
}, "schemas")
_, err := v.Validate(context.Background(), &domain.Artifact{Body: []byte(`{"events":[]}`)}, domain.OutputContract{
ValidationMode: domain.ValidationJSONSchema,
SchemaPath: tc.schemaPath,
})
if err == nil {
t.Fatal("expected schema path error")
}
if !strings.Contains(err.Error(), tc.wantErr) {
t.Fatalf("expected error to contain %q, got %v", tc.wantErr, err)
}
})
}
}
func TestFSValidatorSingleSchemaFileUsesBaseName(t *testing.T) {
v := NewFSValidator(fstest.MapFS{
"events.schema.json": &fstest.MapFile{Data: []byte(`{
"type": "object",
"required": ["events"],
"properties": {
"events": {"type": "array"}
}
}`)},
}, "events.schema.json")
res, err := v.Validate(context.Background(), &domain.Artifact{Body: []byte(`{"events":[]}`)}, domain.OutputContract{
ValidationMode: domain.ValidationJSONSchema,
SchemaPath: "events.schema.json",
})
if err != nil {
t.Fatalf("expected no error, got %v", err)
}
if res.Status != domain.ValidationPassed || !res.IsValid {
t.Fatalf("expected passed/valid, got status=%q valid=%v", res.Status, res.IsValid)
}
_, err = v.Validate(context.Background(), &domain.Artifact{Body: []byte(`{"events":[]}`)}, domain.OutputContract{
ValidationMode: domain.ValidationJSONSchema,
SchemaPath: "other.schema.json",
})
if err == nil {
t.Fatal("expected schema path mismatch error")
}
}
func TestFSValidatorLoadSchemaDocument(t *testing.T) {
v := NewFSValidator(fstest.MapFS{
"schemas/schema.json": &fstest.MapFile{Data: []byte(`{"type":"object"}`)},
}, "schemas")
loader, ok := v.(SchemaDocumentLoader)
if !ok {
t.Fatal("fs validator must implement SchemaDocumentLoader")
}
doc, err := loader.LoadSchemaDocument(context.Background(), "schema.json")
if err != nil {
t.Fatalf("expected no error, got %v", err)
}
obj, ok := doc.(map[string]any)
if !ok || obj["type"] != "object" {
t.Fatalf("unexpected schema document: %#v", doc)
}
}

View File

@@ -0,0 +1,16 @@
package validate
import (
"context"
"gitea.maximumdirect.net/eric/promptkit/internal/domain"
)
// Validator validates the generated artifact based on the output contract.
type Validator interface {
Validate(ctx context.Context, artifact *domain.Artifact, contract domain.OutputContract) (domain.ValidationResult, error)
}
// SchemaDocumentLoader loads JSON schema documents using validator path semantics.
type SchemaDocumentLoader interface {
LoadSchemaDocument(ctx context.Context, schemaPath string) (any, error)
}