promptkit/internal/validate/standard_validator.go

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), "/")
}