Files
notarius/internal/modules/dnd/extract/spells/npc_registry_test.go

237 lines
11 KiB
Go

package spells
import (
"bytes"
"context"
"encoding/json"
"strings"
"testing"
"gitea.maximumdirect.net/eric/notarius/internal/core/source"
"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd"
npccodec "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/codec/npcs"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/npcs/identity"
)
func TestResolveNPCRegistryUsesExactEmptyPromptWhenUnbound(t *testing.T) {
resolved, err := resolveNPCRegistry(contracts.ReferenceSet{})
if err != nil {
t.Fatalf("resolveNPCRegistry() error = %v, want nil", err)
}
if resolved.bound || resolved.digest != "" || resolved.count != 0 {
t.Fatalf("resolved unbound registry = %#v, want no semantic metadata", resolved)
}
if resolved.input.Name != NPCRegistryReferenceSlot || resolved.input.MediaType != "application/json" || resolved.input.Digest != "" || resolved.input.OriginURI != "" {
t.Fatalf("unbound prompt input metadata = %#v, want name/media type only", resolved.input)
}
if got := string(resolved.input.Content); got != `{"npcs":[]}` {
t.Fatalf("unbound prompt input = %q, want exact empty registry", got)
}
if resolved.input.SizeBytes != int64(len(`{"npcs":[]}`)) {
t.Fatalf("unbound prompt input size = %d, want %d", resolved.input.SizeBytes, len(`{"npcs":[]}`))
}
if metadata := newExtractor(t, &fakeSpellsLLMClient{}).ManifestMetadata(); metadata["npc_registry_digest"] != nil || metadata["npc_count"] != nil {
t.Fatalf("unbound extractor metadata = %#v, want no NPC registry fields", metadata)
}
fingerprints := newExtractor(t, &fakeSpellsLLMClient{}).CheckpointFingerprints()
for _, fingerprint := range fingerprints {
if fingerprint.Name == "npc_registry" {
t.Fatalf("unbound checkpoint fingerprints = %#v, want no NPC registry fingerprint", fingerprints)
}
}
}
func TestResolveNPCRegistryCanonicalizesContentAndUsesSemanticDigest(t *testing.T) {
value := validNPCRegistryList()
canonical := encodeNPCRegistry(t, value)
raw := append([]byte(" \n"), canonical...)
raw = append(raw, []byte("\n ")...)
resolved, err := resolveNPCRegistry(npcRegistryReference(raw, "file:///another-session/npcs.json"))
if err != nil {
t.Fatalf("resolveNPCRegistry() error = %v, want nil", err)
}
if !resolved.bound || resolved.count != len(value.NPCs) {
t.Fatalf("resolved registry = %#v, want bound registry with %d NPC", resolved, len(value.NPCs))
}
if !bytes.Equal(resolved.input.Content, canonical) {
t.Fatalf("canonical prompt input = %s, want %s", resolved.input.Content, canonical)
}
if resolved.input.Digest != semanticNPCRegistryDigest(canonical) || resolved.digest != resolved.input.Digest {
t.Fatalf("semantic digest = %q/%q, want %q", resolved.input.Digest, resolved.digest, semanticNPCRegistryDigest(canonical))
}
if resolved.input.OriginURI != "" {
t.Fatalf("prompt input origin = %q, want no provenance path", resolved.input.OriginURI)
}
resolved.input.Content[0] = 'X'
again, err := resolveNPCRegistry(npcRegistryReference(raw, "file:///another-session/npcs.json"))
if err != nil {
t.Fatalf("second resolveNPCRegistry() error = %v, want nil", err)
}
if !bytes.Equal(again.input.Content, canonical) {
t.Fatalf("canonical content changed after caller mutation = %s, want %s", again.input.Content, canonical)
}
}
func TestResolveNPCRegistryRejectsInvalidBoundaryValues(t *testing.T) {
valid := validNPCRegistryList()
second := validNPCRegistryList().NPCs[0]
second.ID = identity.DeriveID("Captain Vale")
second.Name = "Captain Vale"
second.Aliases = []string{"The Greencloak"}
valueWithAliasCollision := dnd.NPCList{NPCs: []dnd.NPC{valid.NPCs[0], second}}
invalidID := valid
invalidID.NPCs[0].ID = "not-an-npc-id"
tests := []struct {
name string
reference contracts.ReferenceSet
wantError string
}{
{name: "zero items", reference: contracts.ReferenceSet{Slots: map[string]contracts.ResolvedReferenceSlot{NPCRegistryReferenceSlot: {Items: []contracts.ReferenceItem{}}}}, wantError: "exactly one"},
{name: "multiple", reference: contracts.ReferenceSet{Slots: map[string]contracts.ResolvedReferenceSlot{NPCRegistryReferenceSlot: {Items: []contracts.ReferenceItem{{Content: []byte(`{"npcs":[]}`)}, {Content: []byte(`{"npcs":[]}`)}}}}}, wantError: "exactly one"},
{name: "wrong media type", reference: npcRegistryReferenceWithMedia([]byte(`{"npcs":[]}`), "text/plain"), wantError: "must be application/json"},
{name: "malformed JSON", reference: npcRegistryReference([]byte(`{"npcs":[`), "file:///private.json"), wantError: "decode NPC registry"},
{name: "unknown field", reference: npcRegistryReference([]byte(`{"npcs":[],"unexpected":true}`), "file:///private.json"), wantError: "unknown field"},
{name: "invalid ID", reference: npcRegistryReference(marshalNPCRegistry(t, invalidID), "file:///private.json"), wantError: "decode NPC registry"},
{name: "alias collision", reference: npcRegistryReference(encodeNPCRegistry(t, valueWithAliasCollision), "file:///private.json"), wantError: string(identity.IssueAliasOwnershipCollision)},
{name: "byte limit", reference: npcRegistryReference(bytes.Repeat([]byte("x"), NPCRegistryMaxBytes+1), "file:///private.json"), wantError: "limit"},
}
for _, test := range tests {
t.Run(test.name, func(t *testing.T) {
_, err := resolveNPCRegistry(test.reference)
if err == nil || !strings.Contains(err.Error(), test.wantError) {
t.Fatalf("resolveNPCRegistry() error = %v, want %q", err, test.wantError)
}
if strings.Contains(err.Error(), "Mira Thorn") || strings.Contains(err.Error(), "The Greencloak") || strings.Contains(err.Error(), "private.json") {
t.Fatalf("error leaked registry content or provenance: %v", err)
}
})
}
}
func TestNPCRegistryFingerprintIsSemanticAndDefensive(t *testing.T) {
value := validNPCRegistryList()
canonical := encodeNPCRegistry(t, value)
pretty, err := json.MarshalIndent(value, "", " ")
if err != nil {
t.Fatalf("MarshalIndent() error = %v", err)
}
first := newExtractor(t, &fakeSpellsLLMClient{}, npcRegistryReference(canonical, "file:///one.json"))
second := newExtractor(t, &fakeSpellsLLMClient{}, npcRegistryReference(pretty, "file:///two.json"))
firstFingerprints := checkpointFingerprintMap(first.CheckpointFingerprints())
secondFingerprints := checkpointFingerprintMap(second.CheckpointFingerprints())
if firstFingerprints["npc_registry"] == "" || firstFingerprints["npc_registry"] != secondFingerprints["npc_registry"] {
t.Fatalf("semantic NPC fingerprints = %#v and %#v, want same npc_registry value", firstFingerprints, secondFingerprints)
}
returned := first.CheckpointFingerprints()
returned[0].Name = "caller-mutated"
if first.CheckpointFingerprints()[0].Name == "caller-mutated" {
t.Fatal("CheckpointFingerprints() returned caller-mutable slice state")
}
changed := validNPCRegistryList()
changed.NPCs[0].Description = "A different description."
changedFingerprint := checkpointFingerprintMap(newExtractor(t, &fakeSpellsLLMClient{}, npcRegistryReference(encodeNPCRegistry(t, changed), "file:///three.json")).CheckpointFingerprints())
if changedFingerprint["npc_registry"] == firstFingerprints["npc_registry"] {
t.Fatalf("semantic NPC fingerprint did not change: %#v", changedFingerprint)
}
metadata := first.ManifestMetadata()
encoded, err := json.Marshal(map[string]any{"metadata": metadata, "fingerprints": firstFingerprints})
if err != nil {
t.Fatalf("marshal metadata: %v", err)
}
for _, forbidden := range []string{"Mira Thorn", "The Greencloak", "another-session", "one.json"} {
if strings.Contains(string(encoded), forbidden) {
t.Fatalf("metadata or fingerprints leaked %q: %s", forbidden, encoded)
}
}
if metadata["npc_registry_digest"] != firstFingerprints["npc_registry"] || metadata["npc_count"] != 1 {
t.Fatalf("NPC registry metadata = %#v, want digest and count only", metadata)
}
}
func TestExtractPassesCanonicalNPCRegistryToLLMWithoutProvenance(t *testing.T) {
client := &fakeSpellsLLMClient{response: extractionResponse{SpellCasts: []spellCastResponse{}}}
canonical := encodeNPCRegistry(t, validNPCRegistryList())
extractor := newExtractor(t, client, npcRegistryReference(append([]byte("\n"), canonical...), "file:///npc-session.json"))
if _, err := extractor.Extract(context.Background(), extractionRequest()); err != nil {
t.Fatalf("Extract() error = %v, want nil", err)
}
input := client.requests[0].Inputs[NPCRegistryReferenceSlot]
if input.Name != NPCRegistryReferenceSlot || input.MediaType != "application/json" || input.Digest != semanticNPCRegistryDigest(canonical) || input.OriginURI != "" {
t.Fatalf("NPC prompt input metadata = %#v, want semantic metadata without provenance", input)
}
if !bytes.Equal(input.Content, canonical) {
t.Fatalf("NPC prompt input = %s, want canonical JSON %s", input.Content, canonical)
}
}
func validNPCRegistryList() dnd.NPCList {
return dnd.NPCList{NPCs: []dnd.NPC{{
ID: identity.DeriveID("Mira Thorn"),
Name: "Mira Thorn",
Aliases: []string{"The Greencloak"},
Description: "A guarded ranger who watches the northern road.",
Relationships: []dnd.NPCRelationship{{
Target: "Captain Vale", Relationship: "reports to",
}},
SourceRefs: []source.SourceRef{{SourceID: "npc-session", StartUnitID: 41, EndUnitID: 43}},
}}}
}
func encodeNPCRegistry(t *testing.T, value dnd.NPCList) []byte {
t.Helper()
content, err := npccodec.New().Encode(value)
if err != nil {
t.Fatalf("encode NPC registry: %v", err)
}
return content
}
func marshalNPCRegistry(t *testing.T, value dnd.NPCList) []byte {
t.Helper()
content, err := json.Marshal(value)
if err != nil {
t.Fatalf("marshal NPC registry: %v", err)
}
return content
}
func npcRegistryReference(content []byte, origin string) contracts.ReferenceSet {
references := npcRegistryReferenceWithMedia(content, "application/json; charset=utf-8")
item := references.Slots[NPCRegistryReferenceSlot].Items[0]
item.Origin.URI = origin
slot := references.Slots[NPCRegistryReferenceSlot]
slot.Items[0] = item
references.Slots[NPCRegistryReferenceSlot] = slot
return references
}
func npcRegistryReferenceWithMedia(content []byte, mediaType string) contracts.ReferenceSet {
return contracts.ReferenceSet{Slots: map[string]contracts.ResolvedReferenceSlot{
NPCRegistryReferenceSlot: {
Slot: contracts.ReferenceSlot{Name: NPCRegistryReferenceSlot, AcceptedMediaTypes: []string{"application/json"}, MaxBytes: NPCRegistryMaxBytes},
Items: []contracts.ReferenceItem{{
SlotName: NPCRegistryReferenceSlot,
MediaType: mediaType,
Content: append([]byte(nil), content...),
Origin: contracts.ReferenceOrigin{Type: "file", URI: "file:///npc-registry.json"},
}},
},
}}
}
func checkpointFingerprintMap(values []pipeline.CheckpointFingerprint) map[string]string {
result := make(map[string]string, len(values))
for _, value := range values {
result[value.Name] = value.Value
}
return result
}