Files
scriptorium/internal/promptdef/filesystem_repository.go

520 lines
14 KiB
Go

package promptdef
import (
"bytes"
"context"
"errors"
"fmt"
"io/fs"
"os"
"path"
"path/filepath"
"strings"
"gitea.maximumdirect.net/eric/scriptorium/internal/domain"
"gitea.maximumdirect.net/eric/scriptorium/internal/filecatalog"
"gopkg.in/yaml.v3"
)
var (
ErrPromptDefinitionNotFound = errors.New("prompt definition not found")
ErrInvalidYAML = errors.New("invalid YAML format")
ErrInvalidPromptDefinition = errors.New("invalid prompt definition configuration")
)
type filesystemRepository struct {
dir string
}
type fsRepository struct {
fsys fs.FS
root string
}
type promptDefinitionFile struct {
ID string `yaml:"id"`
Version string `yaml:"version"`
DefaultProfile *string `yaml:"default_profile"`
Description string `yaml:"description"`
SessionID string `yaml:"session_id"`
Inputs []promptInputFile `yaml:"inputs"`
Messages []promptMessageFile `yaml:"messages"`
Output promptOutputContractFile `yaml:"output"`
}
type promptInputFile struct {
Name string `yaml:"name"`
Required bool `yaml:"required"`
ContentType string `yaml:"content_type"`
Description string `yaml:"description"`
}
type promptMessageFile struct {
Role string `yaml:"role"`
Content string `yaml:"content"`
ContentFile string `yaml:"content_file"`
CacheControl *cacheControlFile `yaml:"cache_control"`
}
type cacheControlFile struct {
Type string `yaml:"type"`
TTL string `yaml:"ttl"`
}
type promptOutputContractFile struct {
Format domain.OutputFormat `yaml:"format"`
ValidationMode domain.ValidationMode `yaml:"validation_mode"`
SchemaPath string `yaml:"schema_path"`
RepairAttempts int `yaml:"repair_attempts"`
}
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)
}
files, err := filecatalog.FindYAMLFiles(ctx, r.dir)
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 := filecatalog.RelativePath(r.dir, fullPath)
fileMatch := filecatalog.Stem(filepath.Base(fullPath)) == id
raw, err := loadPromptDefinitionFile(fullPath)
if err != nil {
if fileMatch || promptDefinitionFileHasID(fullPath, id) {
return nil, fmt.Errorf("%w: %s: %v", ErrInvalidYAML, relPath, err)
}
continue
}
def, err := normalizePromptDefinition(raw, 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 (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
}
func loadPromptDefinitionFile(path string) (*promptDefinitionFile, error) {
data, err := os.ReadFile(path)
if err != nil {
return nil, fmt.Errorf("failed to read prompt definition file: %w", err)
}
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 promptDefinitionFileHasID(path string, id string) bool {
data, err := os.ReadFile(path)
if err != nil {
return false
}
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 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")
}
id := strings.TrimSpace(raw.ID)
if id == "" {
return nil, errors.New("id is required")
}
version := strings.TrimSpace(raw.Version)
if version == "" {
return nil, errors.New("version is required")
}
if len(raw.Messages) == 0 {
return nil, errors.New("at least one message is required")
}
inputs := make([]domain.PromptInput, 0, len(raw.Inputs))
seenInputNames := make(map[string]struct{}, len(raw.Inputs))
for i, in := range raw.Inputs {
name := strings.TrimSpace(in.Name)
if name == "" {
return nil, fmt.Errorf("input %d has empty name", i)
}
if _, exists := seenInputNames[name]; exists {
return nil, fmt.Errorf("duplicate input name %q", name)
}
seenInputNames[name] = struct{}{}
inputs = append(inputs, domain.PromptInput{
Name: name,
Required: in.Required,
ContentType: strings.TrimSpace(in.ContentType),
Description: strings.TrimSpace(in.Description),
})
}
templates := make([]domain.PromptMessageTemplate, 0, len(raw.Messages))
for i, msg := range raw.Messages {
role := strings.TrimSpace(msg.Role)
if role == "" {
return nil, fmt.Errorf("message %d role is required", i)
}
hasContent := strings.TrimSpace(msg.Content) != ""
hasContentFile := strings.TrimSpace(msg.ContentFile) != ""
if hasContent == hasContentFile {
return nil, fmt.Errorf("message %d (%s) must set exactly one of content or content_file", i, role)
}
cacheControl, err := normalizeCacheControl(msg.CacheControl)
if err != nil {
return nil, fmt.Errorf("message %d (%s) cache_control: %w", i, role, err)
}
templateContent := msg.Content
resolvedContentFile := ""
if hasContentFile {
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 = body
resolvedContentFile = resolvedPath
}
templates = append(templates, domain.PromptMessageTemplate{
Role: role,
Content: templateContent,
ContentFile: resolvedContentFile,
CacheControl: cacheControl,
})
}
if !isValidOutputFormat(raw.Output.Format) {
return nil, fmt.Errorf("invalid output format: %q", raw.Output.Format)
}
if !isValidValidationMode(raw.Output.ValidationMode) {
return nil, fmt.Errorf("invalid validation mode: %q", raw.Output.ValidationMode)
}
if raw.Output.ValidationMode == domain.ValidationJSONSchema && strings.TrimSpace(raw.Output.SchemaPath) == "" {
return nil, errors.New("output.schema_path is required when output.validation_mode is json_schema")
}
if raw.Output.RepairAttempts < 0 {
return nil, errors.New("output.repair_attempts must be greater than or equal to 0")
}
defaultProfile := ""
if raw.DefaultProfile != nil {
defaultProfile = strings.TrimSpace(*raw.DefaultProfile)
if defaultProfile == "" {
return nil, errors.New("default_profile must be a non-empty string when set")
}
}
return &domain.PromptDefinition{
ID: id,
Version: version,
DefaultProfile: defaultProfile,
Description: strings.TrimSpace(raw.Description),
SessionID: strings.TrimSpace(raw.SessionID),
Inputs: inputs,
Templates: templates,
OutputFormat: raw.Output.Format,
Validation: domain.OutputContract{
Format: raw.Output.Format,
ValidationMode: raw.Output.ValidationMode,
SchemaPath: strings.TrimSpace(raw.Output.SchemaPath),
RepairAttempts: raw.Output.RepairAttempts,
},
}, nil
}
func normalizeCacheControl(raw *cacheControlFile) (*domain.CacheControl, error) {
if raw == nil {
return nil, nil
}
cacheType := strings.TrimSpace(raw.Type)
if cacheType == "" {
return nil, errors.New("type is required")
}
if domain.CacheControlType(cacheType) != domain.CacheControlEphemeral {
return nil, fmt.Errorf("unsupported type %q", cacheType)
}
ttl := strings.TrimSpace(raw.TTL)
if ttl != "" && ttl != "1h" {
return nil, fmt.Errorf("unsupported ttl %q", ttl)
}
return &domain.CacheControl{
Type: domain.CacheControlType(cacheType),
TTL: ttl,
}, nil
}
func isValidOutputFormat(f domain.OutputFormat) bool {
switch f {
case domain.FormatText, domain.FormatMarkdown, domain.FormatJSON:
return true
default:
return false
}
}
func isValidValidationMode(m domain.ValidationMode) bool {
switch m {
case domain.ValidationNone, domain.ValidationBasic, domain.ValidationJSON, domain.ValidationJSONSchema:
return true
default:
return false
}
}