Move prompts into embedded Markdown assets

internal/prompts/registry.go

@@ -0,0 +1,164 @@
+package prompts
+
+import (
+	"crypto/sha256"
+	"embed"
+	"encoding/hex"
+	"fmt"
+	"path"
+	"sort"
+	"strings"
+	"text/template"
+)
+
+//go:embed assets/**
+var embeddedAssets embed.FS
+
+const (
+	SourceBuiltin = "builtin"
+	VersionV1     = "v1"
+)
+
+const (
+	PromptIDModuleGlossaryProposal   = "modules.glossary.proposal"
+	PromptIDModuleHomophonesProposal = "modules.homophones.proposal"
+	PromptIDModuleSpokenWordProposal = "modules.spoken_word.proposal"
+	PromptIDModuleGrammarProposal    = "modules.grammar.proposal"
+
+	PromptIDValidatorSpokenFormPlausibility = "validators.spoken_form_plausibility"
+	PromptIDValidatorMeaningReversalReview  = "validators.meaning_reversal_review"
+	PromptIDValidatorEditorialReview        = "validators.editorial_review"
+	PromptIDValidatorGrammarReview          = "validators.grammar_review"
+	PromptIDValidatorSpokenWordReview       = "validators.spoken_word_review"
+)
+
+type Metadata struct {
+	PromptID      string `json:"prompt_id"`
+	PromptVersion string `json:"prompt_version"`
+	PromptSource  string `json:"prompt_source"`
+	EmbeddedPath  string `json:"embedded_path"`
+	SHA256        string `json:"sha256"`
+}
+
+type definition struct {
+	id          string
+	version     string
+	embeddedDir string
+	systemPath  string
+	userPath    string
+}
+
+type compiledPrompt struct {
+	def        definition
+	systemTmpl *template.Template
+	userTmpl   *template.Template
+	metadata   Metadata
+}
+
+var promptRegistry map[string]compiledPrompt
+var sharedHardening string
+
+func init() {
+	var err error
+	sharedHardening, err = readAsset("assets/shared/prompt_hardening.md")
+	if err != nil {
+		panic(err)
+	}
+
+	defs := []definition{
+		{id: PromptIDModuleGlossaryProposal, version: VersionV1, embeddedDir: "assets/modules/glossary", systemPath: "assets/modules/glossary/system.md", userPath: "assets/modules/glossary/user.md"},
+		{id: PromptIDModuleHomophonesProposal, version: VersionV1, embeddedDir: "assets/modules/homophones", systemPath: "assets/modules/homophones/system.md", userPath: "assets/modules/homophones/user.md"},
+		{id: PromptIDModuleSpokenWordProposal, version: VersionV1, embeddedDir: "assets/modules/spoken_word", systemPath: "assets/modules/spoken_word/system.md", userPath: "assets/modules/spoken_word/user.md"},
+		{id: PromptIDModuleGrammarProposal, version: VersionV1, embeddedDir: "assets/modules/grammar", systemPath: "assets/modules/grammar/system.md", userPath: "assets/modules/grammar/user.md"},
+		{id: PromptIDValidatorSpokenFormPlausibility, version: VersionV1, embeddedDir: "assets/validators/spoken_form_plausibility", systemPath: "assets/validators/spoken_form_plausibility/system.md", userPath: "assets/validators/spoken_form_plausibility/user.md"},
+		{id: PromptIDValidatorMeaningReversalReview, version: VersionV1, embeddedDir: "assets/validators/meaning_reversal_review", systemPath: "assets/validators/meaning_reversal_review/system.md", userPath: "assets/validators/meaning_reversal_review/user.md"},
+		{id: PromptIDValidatorEditorialReview, version: VersionV1, embeddedDir: "assets/validators/editorial_review", systemPath: "assets/validators/editorial_review/system.md", userPath: "assets/validators/editorial_review/user.md"},
+		{id: PromptIDValidatorGrammarReview, version: VersionV1, embeddedDir: "assets/validators/grammar_review", systemPath: "assets/validators/grammar_review/system.md", userPath: "assets/validators/grammar_review/user.md"},
+		{id: PromptIDValidatorSpokenWordReview, version: VersionV1, embeddedDir: "assets/validators/spoken_word_review", systemPath: "assets/validators/spoken_word_review/system.md", userPath: "assets/validators/spoken_word_review/user.md"},
+	}
+
+	promptRegistry = make(map[string]compiledPrompt, len(defs))
+	for _, def := range defs {
+		cp, cErr := compilePrompt(def)
+		if cErr != nil {
+			panic(cErr)
+		}
+		promptRegistry[def.id] = cp
+	}
+}
+
+func readAsset(assetPath string) (string, error) {
+	b, err := embeddedAssets.ReadFile(assetPath)
+	if err != nil {
+		return "", fmt.Errorf("read embedded prompt asset %q: %w", assetPath, err)
+	}
+	return string(b), nil
+}
+
+func compilePrompt(def definition) (compiledPrompt, error) {
+	systemSource, err := readAsset(def.systemPath)
+	if err != nil {
+		return compiledPrompt{}, err
+	}
+	userSource, err := readAsset(def.userPath)
+	if err != nil {
+		return compiledPrompt{}, err
+	}
+
+	funcs := template.FuncMap{
+		"hardening": func() string { return sharedHardening },
+	}
+	systemTmpl, err := template.New(path.Base(def.systemPath)).Option("missingkey=error").Funcs(funcs).Parse(systemSource)
+	if err != nil {
+		return compiledPrompt{}, fmt.Errorf("parse embedded system prompt %q: %w", def.systemPath, err)
+	}
+	userTmpl, err := template.New(path.Base(def.userPath)).Option("missingkey=error").Funcs(funcs).Parse(userSource)
+	if err != nil {
+		return compiledPrompt{}, fmt.Errorf("parse embedded user prompt %q: %w", def.userPath, err)
+	}
+
+	hashInput := systemSource + "\n\n" + userSource
+	sum := sha256.Sum256([]byte(hashInput))
+	meta := Metadata{
+		PromptID:      def.id,
+		PromptVersion: def.version,
+		PromptSource:  SourceBuiltin,
+		EmbeddedPath:  def.embeddedDir,
+		SHA256:        hex.EncodeToString(sum[:]),
+	}
+
+	return compiledPrompt{def: def, systemTmpl: systemTmpl, userTmpl: userTmpl, metadata: meta}, nil
+}
+
+func LookupMetadata(promptID string) (Metadata, bool) {
+	cp, ok := promptRegistry[strings.TrimSpace(promptID)]
+	if !ok {
+		return Metadata{}, false
+	}
+	return cp.metadata, true
+}
+
+func MustLookupMetadata(promptID string) Metadata {
+	m, ok := LookupMetadata(promptID)
+	if !ok {
+		panic(fmt.Sprintf("unknown prompt id %q", promptID))
+	}
+	return m
+}
+
+func RegisteredMetadata() []Metadata {
+	ids := make([]string, 0, len(promptRegistry))
+	for id := range promptRegistry {
+		ids = append(ids, id)
+	}
+	sort.Strings(ids)
+	out := make([]Metadata, 0, len(ids))
+	for _, id := range ids {
+		out = append(out, promptRegistry[id].metadata)
+	}
+	return out
+}
+
+func HardeningText() string {
+	return sharedHardening
+}