Add public asset source options

This commit is contained in:
2026-07-04 17:02:09 +00:00
parent 3ad247039b
commit 6f91603168
8 changed files with 978 additions and 26 deletions

View File

@@ -5,7 +5,9 @@ import (
"context"
"errors"
"fmt"
"io/fs"
"os"
"path"
"path/filepath"
"strings"
@@ -24,6 +26,11 @@ type filesystemRepository struct {
dir string
}
type fsRepository struct {
fsys fs.FS
root string
}
type promptDefinitionFile struct {
ID string `yaml:"id"`
Version string `yaml:"version"`
@@ -65,6 +72,10 @@ func NewFilesystemRepository(dir string) Repository {
return &filesystemRepository{dir: dir}
}
func NewFSRepository(fsys fs.FS, root string) Repository {
return &fsRepository{fsys: fsys, root: root}
}
func (r *filesystemRepository) GetPromptDefinition(ctx context.Context, id string, version string) (*domain.PromptDefinition, error) {
if strings.TrimSpace(id) == "" {
return nil, fmt.Errorf("%w: prompt id is required", ErrInvalidPromptDefinition)
@@ -132,6 +143,10 @@ func (r *filesystemRepository) GetPromptDefinition(ctx context.Context, id strin
return nil, ErrPromptDefinitionNotFound
}
func (r *fsRepository) GetPromptDefinition(ctx context.Context, id string, version string) (*domain.PromptDefinition, error) {
return loadPromptDefinition(ctx, r.fsys, r.root, id, version)
}
type promptDefinitionMatch struct {
def *domain.PromptDefinition
path string
@@ -166,7 +181,187 @@ func promptDefinitionFileHasID(path string, id string) bool {
return strings.TrimSpace(raw.ID) == id
}
func loadPromptDefinition(ctx context.Context, fsys fs.FS, root string, id string, version string) (*domain.PromptDefinition, error) {
if strings.TrimSpace(id) == "" {
return nil, fmt.Errorf("%w: prompt id is required", ErrInvalidPromptDefinition)
}
if fsys == nil {
return nil, fmt.Errorf("failed to read prompt definition directory: filesystem is nil")
}
files, err := findPromptDefinitionYAMLFiles(ctx, fsys, root)
if err != nil {
return nil, fmt.Errorf("failed to read prompt definition directory: %w", err)
}
var matches []promptDefinitionMatch
for _, fullPath := range files {
select {
case <-ctx.Done():
return nil, ctx.Err()
default:
}
relPath := displayPath(root, fullPath)
fileMatch := filecatalog.Stem(path.Base(fullPath)) == id
data, err := fs.ReadFile(fsys, fullPath)
if err != nil {
if fileMatch {
return nil, fmt.Errorf("%w: %s: failed to read prompt definition file: %v", ErrInvalidYAML, relPath, err)
}
continue
}
raw, err := decodePromptDefinition(data)
if err != nil {
if fileMatch || promptDefinitionDataHasID(data, id) {
return nil, fmt.Errorf("%w: %s: %v", ErrInvalidYAML, relPath, err)
}
continue
}
def, err := normalizePromptDefinitionFromFS(raw, fsys, fullPath)
if err != nil {
if fileMatch || strings.TrimSpace(raw.ID) == id {
return nil, fmt.Errorf("%w: %s: %v", ErrInvalidPromptDefinition, relPath, err)
}
continue
}
if def.ID != id {
continue
}
if version != "" && def.Version != version {
continue
}
matches = append(matches, promptDefinitionMatch{
def: def,
path: relPath,
})
}
if len(matches) > 1 {
paths := make([]string, 0, len(matches))
for _, match := range matches {
paths = append(paths, match.path)
}
if version != "" {
return nil, fmt.Errorf("%w: duplicate prompt definition id %q version %q found in: %s", ErrInvalidPromptDefinition, id, version, strings.Join(paths, ", "))
}
return nil, fmt.Errorf("%w: duplicate prompt definition id %q found in: %s", ErrInvalidPromptDefinition, id, strings.Join(paths, ", "))
}
if len(matches) == 1 {
return matches[0].def, nil
}
return nil, ErrPromptDefinitionNotFound
}
func findPromptDefinitionYAMLFiles(ctx context.Context, fsys fs.FS, root string) ([]string, error) {
cleanRoot := cleanFSRoot(root)
var files []string
err := fs.WalkDir(fsys, cleanRoot, func(name string, d fs.DirEntry, err error) error {
if err != nil {
return err
}
select {
case <-ctx.Done():
return ctx.Err()
default:
}
if d.IsDir() {
return nil
}
if !isPromptDefinitionYAMLFile(d.Name()) {
return nil
}
files = append(files, name)
return nil
})
return files, err
}
func cleanFSRoot(root string) string {
root = strings.TrimSpace(root)
if root == "" || root == "." {
return "."
}
return path.Clean(root)
}
func displayPath(root string, name string) string {
cleanRoot := cleanFSRoot(root)
cleanName := path.Clean(name)
if cleanRoot == "." {
return cleanName
}
prefix := strings.TrimSuffix(cleanRoot, "/") + "/"
if strings.HasPrefix(cleanName, prefix) {
return strings.TrimPrefix(cleanName, prefix)
}
return cleanName
}
func isPromptDefinitionYAMLFile(name string) bool {
return strings.HasSuffix(name, ".yaml") || strings.HasSuffix(name, ".yml")
}
func decodePromptDefinition(data []byte) (*promptDefinitionFile, error) {
var raw promptDefinitionFile
decoder := yaml.NewDecoder(bytes.NewReader(data))
decoder.KnownFields(true)
if err := decoder.Decode(&raw); err != nil {
return nil, err
}
return &raw, nil
}
func promptDefinitionDataHasID(data []byte, id string) bool {
var raw struct {
ID string `yaml:"id"`
}
if err := yaml.NewDecoder(bytes.NewReader(data)).Decode(&raw); err != nil {
return false
}
return strings.TrimSpace(raw.ID) == id
}
func normalizePromptDefinition(raw *promptDefinitionFile, sourcePath string) (*domain.PromptDefinition, error) {
promptDir := filepath.Dir(sourcePath)
return normalizePromptDefinitionWithContent(raw, func(contentFile string) (string, string, error) {
resolvedPath := strings.TrimSpace(contentFile)
if !filepath.IsAbs(resolvedPath) {
resolvedPath = filepath.Join(promptDir, resolvedPath)
}
resolvedPath = filepath.Clean(resolvedPath)
body, err := os.ReadFile(resolvedPath)
if err != nil {
return "", "", err
}
return string(body), resolvedPath, nil
})
}
func normalizePromptDefinitionFromFS(raw *promptDefinitionFile, fsys fs.FS, sourcePath string) (*domain.PromptDefinition, error) {
promptDir := path.Dir(sourcePath)
return normalizePromptDefinitionWithContent(raw, func(contentFile string) (string, string, error) {
resolvedPath := strings.TrimSpace(contentFile)
if !path.IsAbs(resolvedPath) {
resolvedPath = path.Join(promptDir, resolvedPath)
}
resolvedPath = strings.TrimPrefix(path.Clean(resolvedPath), "/")
body, err := fs.ReadFile(fsys, resolvedPath)
if err != nil {
return "", "", err
}
return string(body), resolvedPath, nil
})
}
func normalizePromptDefinitionWithContent(raw *promptDefinitionFile, readContentFile func(string) (string, string, error)) (*domain.PromptDefinition, error) {
if raw == nil {
return nil, errors.New("prompt definition is nil")
}
@@ -206,7 +401,6 @@ func normalizePromptDefinition(raw *promptDefinitionFile, sourcePath string) (*d
}
templates := make([]domain.PromptMessageTemplate, 0, len(raw.Messages))
promptDir := filepath.Dir(sourcePath)
for i, msg := range raw.Messages {
role := strings.TrimSpace(msg.Role)
if role == "" {
@@ -227,17 +421,11 @@ func normalizePromptDefinition(raw *promptDefinitionFile, sourcePath string) (*d
templateContent := msg.Content
resolvedContentFile := ""
if hasContentFile {
resolvedPath := strings.TrimSpace(msg.ContentFile)
if !filepath.IsAbs(resolvedPath) {
resolvedPath = filepath.Join(promptDir, resolvedPath)
}
resolvedPath = filepath.Clean(resolvedPath)
body, err := os.ReadFile(resolvedPath)
body, resolvedPath, err := readContentFile(msg.ContentFile)
if err != nil {
return nil, fmt.Errorf("prompt %q message %d (%s): failed to read content_file %q: %w", id, i, role, msg.ContentFile, err)
}
templateContent = string(body)
templateContent = body
resolvedContentFile = resolvedPath
}

View File

@@ -8,6 +8,7 @@ import (
"path/filepath"
"strings"
"testing"
"testing/fstest"
"gitea.maximumdirect.net/eric/scriptorium/internal/domain"
)
@@ -324,6 +325,97 @@ output:
})
}
func TestFSRepositoryGetPromptDefinition(t *testing.T) {
repo := NewFSRepository(fstest.MapFS{
"prompts/nested/prompt.yaml": &fstest.MapFile{Data: []byte(`
id: fs-prompt
version: "1.0.0"
inputs:
- name: transcript
required: true
messages:
- role: user
content_file: ./messages/user.tmpl
output:
format: markdown
validation_mode: basic
repair_attempts: 0
`)},
"prompts/nested/messages/user.tmpl": &fstest.MapFile{Data: []byte(`Summarize {{input "transcript"}}.`)},
}, "prompts")
got, err := repo.GetPromptDefinition(context.Background(), "fs-prompt", "")
if err != nil {
t.Fatalf("expected no error, got %v", err)
}
if got.ID != "fs-prompt" {
t.Fatalf("unexpected prompt id: %q", got.ID)
}
if len(got.Templates) != 1 || !strings.Contains(got.Templates[0].Content, `{{input "transcript"}}`) {
t.Fatalf("expected content_file body to be loaded, got %+v", got.Templates)
}
if got.Templates[0].ContentFile != "prompts/nested/messages/user.tmpl" {
t.Fatalf("unexpected content file path: %q", got.Templates[0].ContentFile)
}
}
func TestFSRepositoryRejectsDuplicatePromptIDs(t *testing.T) {
repo := NewFSRepository(fstest.MapFS{
"one.yaml": &fstest.MapFile{Data: []byte(`
id: duplicate-fs-prompt
version: "1.0.0"
messages:
- role: user
content: First.
output:
format: text
validation_mode: none
repair_attempts: 0
`)},
"nested/two.yaml": &fstest.MapFile{Data: []byte(`
id: duplicate-fs-prompt
version: "1.0.0"
messages:
- role: user
content: Second.
output:
format: text
validation_mode: none
repair_attempts: 0
`)},
}, ".")
_, err := repo.GetPromptDefinition(context.Background(), "duplicate-fs-prompt", "")
if !errors.Is(err, ErrInvalidPromptDefinition) {
t.Fatalf("expected ErrInvalidPromptDefinition, got %v", err)
}
if !strings.Contains(err.Error(), "one.yaml") || !strings.Contains(err.Error(), "nested/two.yaml") {
t.Fatalf("expected duplicate paths in error, got %v", err)
}
}
func TestFSRepositoryRejectsUnknownYAMLFields(t *testing.T) {
repo := NewFSRepository(fstest.MapFS{
"not_named_like_id.yaml": &fstest.MapFile{Data: []byte(`
id: strict-fs-prompt
version: "1.0.0"
unknown: true
messages:
- role: user
content: Invalid.
output:
format: text
validation_mode: none
repair_attempts: 0
`)},
}, ".")
_, err := repo.GetPromptDefinition(context.Background(), "strict-fs-prompt", "")
if !errors.Is(err, ErrInvalidYAML) {
t.Fatalf("expected ErrInvalidYAML, got %v", err)
}
}
func assertCacheControl(t *testing.T, got *domain.CacheControl, wantType domain.CacheControlType, wantTTL string) {
t.Helper()
if got == nil {

View File

@@ -5,7 +5,9 @@ import (
"encoding/json"
"errors"
"fmt"
"io/fs"
"os"
"path"
"path/filepath"
"strings"
@@ -18,10 +20,19 @@ 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) {
select {
case <-ctx.Done():
@@ -100,6 +111,88 @@ func (v *StandardValidator) Validate(ctx context.Context, artifact *domain.Artif
}
}
func (v *FSValidator) Validate(ctx context.Context, artifact *domain.Artifact, contract domain.OutputContract) (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
}
schemaName, schemaDoc, err := v.loadSchemaDocument(contract.SchemaPath)
if err != nil {
return domain.ValidationResult{}, err
}
resourceURL := fsSchemaResourceURL(schemaName)
compiler := jsonschema.NewCompiler()
if err := compiler.AddResource(resourceURL, schemaDoc); err != nil {
return domain.ValidationResult{}, fmt.Errorf("failed to register JSON schema %q: %w", schemaName, err)
}
schema, err := compiler.Compile(resourceURL)
if err != nil {
return domain.ValidationResult{}, fmt.Errorf("failed to compile JSON schema %q: %w", schemaName, err)
}
if err := schema.Validate(instance); err != nil {
res.Status = domain.ValidationFailed
res.IsValid = false
res.Errors = []string{fmt.Sprintf("json schema validation failed: %v", err)}
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 parseJSON(body []byte) (any, error) {
var v any
if err := json.Unmarshal(body, &v); err != nil {
@@ -132,6 +225,20 @@ func (v *StandardValidator) LoadSchemaDocument(ctx context.Context, schemaPath s
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")
@@ -149,3 +256,70 @@ func (v *StandardValidator) resolveSchemaPath(schemaPath string) (string, error)
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 := 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)
}
cleanSchemaPath := cleanSchemaFSPath(schemaPath)
var resolved string
if rootInfo.IsDir() {
resolved = path.Join(cleanRoot, cleanSchemaPath)
} else {
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 {
cleaned := strings.TrimSpace(schemaPath)
cleaned = strings.TrimPrefix(path.Clean(cleaned), "/")
return cleaned
}
func cleanFSRoot(root string) string {
root = strings.TrimSpace(root)
if root == "" || root == "." {
return "."
}
return strings.TrimPrefix(path.Clean(root), "/")
}
func fsSchemaResourceURL(schemaName string) string {
return "scriptorium-schema:///" + strings.TrimPrefix(path.Clean(schemaName), "/")
}

View File

@@ -5,6 +5,7 @@ import (
"os"
"path/filepath"
"testing"
"testing/fstest"
"gitea.maximumdirect.net/eric/scriptorium/internal/domain"
)
@@ -250,3 +251,77 @@ func TestStandardValidatorLoadSchemaDocumentInvalidJSON(t *testing.T) {
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 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)
}
}