Files
notarius/internal/modules/dnd/normalize/npcs/normalizer_test.go

191 lines
8.5 KiB
Go

package npcs
import (
"context"
"encoding/json"
"reflect"
"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"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/npcs/identity"
)
func TestModuleContractAndIdentity(t *testing.T) {
if _, err := DecodeOptions(nil); err != nil {
t.Fatalf("DecodeOptions(nil) error = %v, want nil", err)
}
if _, err := DecodeOptions(map[string]any{"unexpected": true}); err == nil {
t.Fatal("DecodeOptions() accepted unknown option")
}
want := pipeline.ModuleSpec{Key: Key, Stage: pipeline.StageNormalize, ExecutionClass: contracts.ExecutionClassLLMBacked, Requires: []string{"merged"}, Provides: []string{"normalized"}, ArtifactKind: dnd.NPCListKind}
if got := ModuleSpec(); !reflect.DeepEqual(got, want) {
t.Fatalf("ModuleSpec() = %#v, want %#v", got, want)
}
registry := pipeline.NewNormalizerRegistry()
if err := Register(registry); err != nil {
t.Fatalf("Register() error = %v", err)
}
if _, err := New(nil, Options{}); err == nil {
t.Fatal("New(nil, Options{}) error = nil, want nil client rejection")
}
normalizer := newNormalizer(t, &recordingNPCNormalizerClient{})
if metadata := normalizer.ManifestMetadata(); metadata["identity_policy"] != identity.Policy || metadata["normalization_policy"] != normalizationPolicy || metadata["prompt_id"] != PromptID || metadata["semantic_context_policy"] != semanticContextPolicy || metadata["semantic_context_radius"] != semanticContextRadius {
t.Fatalf("metadata = %#v", metadata)
}
wantFingerprints := []pipeline.CheckpointFingerprint{{Name: "prompt", Value: normalizer.promptSHA}, {Name: "response_schema", Value: normalizer.responseSchemaSHA}, {Name: "identity_policy", Value: identity.Policy}, {Name: "normalization_policy", Value: normalizationPolicy}, {Name: "semantic_context_policy", Value: semanticContextPolicy + ":2"}}
if got := normalizer.CheckpointFingerprints(); !reflect.DeepEqual(got, wantFingerprints) {
t.Fatalf("fingerprints = %#v, want %#v", got, wantFingerprints)
}
}
func TestNormalizeNamesEvidenceAndIDs(t *testing.T) {
input := dnd.NPCList{NPCs: []dnd.NPC{{
ID: "wrong", Name: " Lady\tAsh ", SourceRefs: []source.SourceRef{
{SourceID: "b", StartUnitID: 2, EndUnitID: 3},
{SourceID: "a", StartUnitID: 4, EndUnitID: 4},
{SourceID: "b", StartUnitID: 2, EndUnitID: 3},
},
}}}
result, err := newNormalizer(t, &recordingNPCNormalizerClient{}).Normalize(context.Background(), normalizeRequest(input))
if err != nil {
t.Fatalf("Normalize() error = %v", err)
}
want := dnd.NPC{ID: identity.DeriveID("Lady Ash"), Name: "Lady Ash", SourceRefs: []source.SourceRef{{SourceID: "a", StartUnitID: 4, EndUnitID: 4}, {SourceID: "b", StartUnitID: 2, EndUnitID: 3}}}
if !reflect.DeepEqual(result.Value.NPCs[0], want) {
t.Fatalf("NPC = %#v, want %#v", result.Value.NPCs[0], want)
}
for _, reason := range []string{ReasonCodeNPCFieldsNormalized, ReasonCodeSourceReferencesNormalized, ReasonCodeNPCIDRecomputed} {
if !hasWarning(result.Warnings, reason, "npcs[0]") {
t.Fatalf("warnings = %#v, want %s", result.Warnings, reason)
}
}
}
func TestNormalizeOrdersEvidenceBySourceDocumentPosition(t *testing.T) {
doc := &source.SourceDocument{ID: "source", Units: []source.SourceUnit{{ID: 30}, {ID: 10}}}
input := dnd.NPCList{NPCs: []dnd.NPC{{Name: "Lady Ash", SourceRefs: []source.SourceRef{
{SourceID: doc.ID, StartUnitID: 10, EndUnitID: 10},
{SourceID: doc.ID, StartUnitID: 30, EndUnitID: 30},
{SourceID: doc.ID, StartUnitID: 999, EndUnitID: 999},
}}}}
result, err := newNormalizer(t, &recordingNPCNormalizerClient{}).Normalize(context.Background(), normalizeRequestWithSource(input, doc))
if err != nil {
t.Fatalf("Normalize() error = %v", err)
}
got := result.Value.NPCs[0].SourceRefs
if got[0].StartUnitID != 30 || got[1].StartUnitID != 10 || got[2].StartUnitID != 999 {
t.Fatalf("source refs = %#v, want source-document order followed by invalid reference", got)
}
}
func TestNormalizeConsolidatesCanonicalNamesOnlyAndUnionsEvidence(t *testing.T) {
input := dnd.NPCList{NPCs: []dnd.NPC{
{Name: " Captain Vale ", SourceRefs: []source.SourceRef{{SourceID: "a", StartUnitID: 1, EndUnitID: 1}}},
{Name: "captain vale", SourceRefs: []source.SourceRef{{SourceID: "b", StartUnitID: 2, EndUnitID: 2}}},
{Name: "The Captain", SourceRefs: []source.SourceRef{{SourceID: "c", StartUnitID: 3, EndUnitID: 3}}},
}}
result, err := newNormalizer(t, &recordingNPCNormalizerClient{}).Normalize(context.Background(), normalizeRequest(input))
if err != nil {
t.Fatalf("Normalize() error = %v", err)
}
if len(result.Value.NPCs) != 2 || result.Value.NPCs[0].Name != "Captain Vale" || result.Value.NPCs[1].Name != "The Captain" {
t.Fatalf("NPCs = %#v, want name-only stable consolidation", result.Value.NPCs)
}
if refs := result.Value.NPCs[0].SourceRefs; len(refs) != 2 || refs[0].SourceID != "a" || refs[1].SourceID != "b" {
t.Fatalf("source refs = %#v, want evidence union", refs)
}
if !hasWarning(result.Warnings, ReasonCodeDuplicateNPCCollapsed, "npcs[0]") {
t.Fatalf("warnings = %#v, want duplicate collapse", result.Warnings)
}
}
func TestNormalizePreservesInvalidCandidatesAndDoesNotAliasInput(t *testing.T) {
input := dnd.NPCList{NPCs: []dnd.NPC{{Name: " ", SourceRefs: []source.SourceRef{{SourceID: "source", StartUnitID: 0, EndUnitID: -1}}}}}
before := dnd.NPCList{NPCs: []dnd.NPC{{Name: " ", SourceRefs: []source.SourceRef{{SourceID: "source", StartUnitID: 0, EndUnitID: -1}}}}}
result, err := newNormalizer(t, &recordingNPCNormalizerClient{}).Normalize(context.Background(), normalizeRequest(input))
if err != nil || !reflect.DeepEqual(input, before) {
t.Fatalf("Normalize() = %#v, %v; input mutated to %#v", result, err, input)
}
if result.Value.NPCs[0].Name != "" || result.Value.NPCs[0].SourceRefs[0].EndUnitID != -1 {
t.Fatalf("candidate = %#v, want invalid semantics preserved", result.Value.NPCs[0])
}
result.Value.NPCs[0].SourceRefs[0].SourceID = "changed"
if input.NPCs[0].SourceRefs[0].SourceID != "source" {
t.Fatal("output aliases input evidence")
}
}
func TestNormalizeHandlesNilAndCanceledCalls(t *testing.T) {
normalizer := newNormalizer(t, &recordingNPCNormalizerClient{})
result, err := normalizer.Normalize(context.Background(), normalizeRequest(dnd.NPCList{NPCs: nil}))
if err != nil || result.Value.NPCs != nil {
t.Fatalf("nil list result = %#v, error = %v", result.Value, err)
}
canceled, cancel := context.WithCancel(context.Background())
cancel()
if _, err := normalizer.Normalize(canceled, normalizeRequest(dnd.NPCList{})); err == nil || !strings.Contains(err.Error(), "context error") {
t.Fatalf("canceled Normalize() error = %v", err)
}
}
type recordingNPCNormalizerClient struct {
response string
responses []string
err error
requests []contracts.StructuredCompletionRequest
}
func (c *recordingNPCNormalizerClient) CompleteStructured(_ context.Context, request contracts.StructuredCompletionRequest, output any) (contracts.StructuredCompletionResponse, error) {
c.requests = append(c.requests, request)
if c.err != nil {
return contracts.StructuredCompletionResponse{}, c.err
}
response := c.response
if len(c.responses) > 0 {
responseIndex := len(c.requests) - 1
if responseIndex >= len(c.responses) {
responseIndex = len(c.responses) - 1
}
response = c.responses[responseIndex]
}
if response == "" {
response = `{"duplicate_groups":[]}`
}
if err := json.Unmarshal([]byte(response), output); err != nil {
return contracts.StructuredCompletionResponse{}, err
}
return contracts.StructuredCompletionResponse{Content: json.RawMessage(response)}, nil
}
func newNormalizer(t *testing.T, client contracts.StructuredLLMClient) *Normalizer {
t.Helper()
normalizer, err := New(client, Options{})
if err != nil {
t.Fatalf("New() error = %v", err)
}
return normalizer
}
func normalizeRequest(value dnd.NPCList) contracts.TypedNormalizeRequest[dnd.NPCList] {
return contracts.TypedNormalizeRequest[dnd.NPCList]{MergeOutput: contracts.MergeArtifact[dnd.NPCList]{Value: value}}
}
func normalizeRequestWithSource(value dnd.NPCList, doc *source.SourceDocument) contracts.TypedNormalizeRequest[dnd.NPCList] {
request := normalizeRequest(value)
request.Source = doc
return request
}
func hasWarning(warnings []contracts.Warning, reason, scope string) bool {
for _, warning := range warnings {
if warning.ReasonCode == reason && warning.Scope == scope {
return true
}
}
return false
}