Protect deterministic D&D prompt inputs

This commit is contained in:
2026-07-21 14:04:52 +00:00
parent e01b8d1b6d
commit 447c4f73f9
4 changed files with 183 additions and 67 deletions

View File

@@ -1,11 +1,14 @@
package combatturns
import (
"context"
"io/fs"
"strings"
"testing"
"time"
"gitea.maximumdirect.net/eric/notarius/internal/framework/llm"
"gitea.maximumdirect.net/eric/scriptorium"
)
func TestRegisterPromptAssetsAndPrepareCombatPrompt(t *testing.T) {
@@ -42,3 +45,50 @@ func TestRegisterPromptAssetsAndPrepareCombatPrompt(t *testing.T) {
t.Fatalf("scriptoriumPromptMetadata() = %q, %v; want digest", hash, err)
}
}
func TestScriptoriumPromptPreparesRequiredInputs(t *testing.T) {
registry := llm.NewAssetRegistry()
if err := RegisterPromptAssets(registry); err != nil {
t.Fatalf("RegisterPromptAssets() error = %v, want nil", err)
}
options, err := registry.ScriptoriumOptions()
if err != nil {
t.Fatalf("ScriptoriumOptions() error = %v, want nil", err)
}
options = append(options, scriptorium.WithProfiles(scriptorium.OpenAICompatibleProfile(scriptorium.OpenAICompatibleProfileConfig{
ID: "combat-test-profile", Endpoint: "http://127.0.0.1:1/v1", Model: "combat-test-model",
})))
engine, err := scriptorium.NewEngine(scriptorium.Config{Timeout: time.Second}, options...)
if err != nil {
t.Fatalf("NewEngine() error = %v, want nil", err)
}
transcript := `{"units":[1]}`
prepared, err := engine.Prepare(context.Background(), scriptorium.RunRequest{
PromptID: PromptID, PromptVersion: SchemaVersion, ProfileID: "combat-test-profile",
Inputs: map[string]scriptorium.ArtifactRef{
"transcript": scriptorium.InlineWithURI("file:///session.json", transcript),
"players": scriptorium.Inline("Dana: Mira"),
"party": scriptorium.Inline("Mira: ranger"),
"glossary": scriptorium.Inline("Greencloak: title"),
"npcs": scriptorium.Inline(`{"npcs":[]}`),
},
})
if err != nil {
t.Fatalf("Prepare() error = %v, want nil", err)
}
if prepared.PromptID != PromptID || prepared.OutputContract.SchemaPath != "dnd_combat_turns_llm.v1.json" {
t.Fatalf("prepared prompt = %#v, want combat prompt identity and schema", prepared)
}
for _, want := range []string{transcript, "Dana: Mira", "Mira: ranger", "Greencloak: title", `{"npcs":[]}`} {
found := false
for _, message := range prepared.Messages {
if strings.Contains(message.Content, want) {
found = true
break
}
}
if !found {
t.Fatalf("prepared prompt did not render required input %q", want)
}
}
}

View File

@@ -39,14 +39,29 @@ func TestRegisterPromptAssetsAndPrepareNPCPrompt(t *testing.T) {
if err != nil {
t.Fatalf("Prepare() error = %v, want nil", err)
}
if prepared.PromptID != PromptID || prepared.OutputContract.SchemaPath != "dnd_npcs_llm.v1.json" || len(prepared.Messages) != 5 {
if prepared.PromptID != PromptID || prepared.OutputContract.SchemaPath != "dnd_npcs_llm.v1.json" {
t.Fatalf("prepared prompt = %#v, want NPC prompt identity and wiring", prepared)
}
if !strings.Contains(prepared.Messages[1].Content, `{"units":[1]}`) || !strings.Contains(prepared.Messages[2].Content, "Dana: Mira") || !strings.Contains(prepared.Messages[2].Content, "Mira: ranger") {
t.Fatalf("prepared prompt inputs do not include transcript/references")
for _, want := range []string{`{"units":[1]}`, "Dana: Mira", "Mira: ranger", "Greencloak: title"} {
found := false
for _, message := range prepared.Messages {
if strings.Contains(message.Content, want) {
found = true
break
}
}
if !found {
t.Fatalf("prepared prompt did not render required input %q", want)
}
}
if strings.Contains(prepared.Messages[3].Content, `{"units":[1]}`) || strings.Contains(prepared.Messages[4].Content, `{"units":[1]}`) {
t.Fatal("task or instruction prompt leaked raw transcript")
transcriptMessages := 0
for _, message := range prepared.Messages {
if strings.Contains(message.Content, `{"units":[1]}`) {
transcriptMessages++
}
}
if transcriptMessages != 1 {
t.Fatalf("raw transcript rendered in %d messages, want exactly one", transcriptMessages)
}
}

View File

@@ -21,32 +21,24 @@ func TestScriptoriumPromptPreparesTranscriptReferencesAndTaskMessages(t *testing
if prepared.OutputContract.SchemaPath != "dnd_spells_llm.v1.json" {
t.Fatalf("schema path = %q, want LLM-only schema", prepared.OutputContract.SchemaPath)
}
if got := len(prepared.Messages); got != 7 {
t.Fatalf("message count = %d, want 7", got)
}
if !strings.Contains(prepared.Messages[1].Content, string(transcript)) {
t.Fatalf("transcript message did not include source input")
}
if prepared.Messages[1].CacheControl == nil || prepared.Messages[2].CacheControl == nil {
t.Fatalf("expected transcript and reference messages to be cacheable: %#v", prepared.Messages)
}
if !strings.Contains(prepared.Messages[2].Content, "Dana: Mira") {
t.Fatalf("reference message missing player content")
}
if !strings.Contains(prepared.Messages[2].Content, "Mira: wizard") {
t.Fatalf("reference message missing party content")
}
if !strings.Contains(prepared.Messages[2].Content, "Shield: abjuration") {
t.Fatalf("reference message missing glossary content")
}
if !strings.Contains(prepared.Messages[4].Content, `{"spell_names":["Cure Wounds"]}`) {
t.Fatalf("catalog message missing canonical spell-name input: %s", prepared.Messages[4].Content)
}
if !strings.Contains(prepared.Messages[3].Content, `{"npcs":[]}`) {
t.Fatalf("NPC registry message missing empty registry input: %s", prepared.Messages[3].Content)
}
if strings.Contains(prepared.Messages[5].Content, string(transcript)) {
t.Fatalf("task message leaked transcript bytes")
for _, want := range []string{
string(transcript),
"Dana: Mira",
"Mira: wizard",
"Shield: abjuration",
`{"spell_names":["Cure Wounds"]}`,
`{"npcs":[]}`,
} {
found := false
for _, message := range prepared.Messages {
if strings.Contains(message.Content, want) {
found = true
break
}
}
if !found {
t.Fatalf("prepared prompt did not render required input %q", want)
}
}
}