Files
notarius/internal/modules/integration/dnd_npc_occurrences_runner_test.go

340 lines
14 KiB
Go

package integration_test
import (
"context"
"encoding/json"
"fmt"
"os"
"reflect"
"strings"
"sync"
"testing"
"gitea.maximumdirect.net/eric/notarius/internal/core/config"
"gitea.maximumdirect.net/eric/notarius/internal/core/source"
"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
occurrencecodec "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/codec/npcoccurrences"
npccodec "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/codec/npcregistry"
occurrenceextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/npcoccurrences"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/npcregistry"
npcnormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/npcregistry"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/npcs/identity"
)
func TestNPCOccurrencePipelineUsesAcceptedRegistryAndCurrentEvidence(t *testing.T) {
registries := productionNPCRegistries(t)
resolved := resolveNPCOccurrencePipeline(t, registries)
client := &npcOccurrenceLLMClient{}
output, err := runPreparedPipeline(t, registries, resolved, client, pipeline.RunInput{RawInput: readNPCFixture(t)})
if err != nil {
t.Fatalf("Run() error = %v", err)
}
if len(output.Rejected) != 0 || len(output.NormalizeOutputs) != 2 {
t.Fatalf("run outputs = %#v rejected = %#v, want NPC and occurrence artifacts", output.NormalizeOutputs, output.Rejected)
}
request := client.requestFor(t, occurrenceextract.PromptID)
wantRegistry := `{"npcs":[{"name":"Mira Thorn"},{"name":"Hooded Guard"}]}`
if got := string(request.Inputs["npc_registry"].Content); got != wantRegistry {
t.Fatalf("occurrence registry input = %s, want names-only projection %s", got, wantRegistry)
}
if request.Inputs["npc_registry"].MediaType != npccodec.MediaType {
t.Fatalf("occurrence registry media type = %q, want %q", request.Inputs["npc_registry"].MediaType, npccodec.MediaType)
}
serialized := normalizedLane(t, output, "occurrences")
if serialized.Artifact.Schema.ID != occurrencecodec.SchemaID || serialized.Artifact.Schema.Version != occurrencecodec.SchemaVersion {
t.Fatalf("occurrence artifact schema = %#v", serialized.Artifact.Schema)
}
occurrences, err := occurrencecodec.New().Decode(serialized.Artifact.Content)
if err != nil {
t.Fatalf("Decode(occurrence output) error = %v", err)
}
if len(occurrences.Occurrences) != 2 {
t.Fatalf("occurrences = %#v, want two occurrences", occurrences)
}
first, second := occurrences.Occurrences[0], occurrences.Occurrences[1]
if first.Name != "Mira Thorn" || string(first.Kind) != "dialogue" || second.Name != "Hooded Guard" || string(second.Kind) != "noncombat_presence" {
t.Fatalf("occurrences = %#v, want canonical names, kinds, and source chronology", occurrences)
}
if first.NPCID != identity.DeriveID("Mira Thorn") || second.NPCID != identity.DeriveID("Hooded Guard") {
t.Fatalf("occurrences = %#v, want durable registry IDs", occurrences)
}
assertOccurrenceEvidence(t, first.SourceRefs)
assertOccurrenceEvidence(t, second.SourceRefs)
if first.SourceRefs[0].StartUnitID >= second.SourceRefs[0].StartUnitID {
t.Fatalf("occurrence chronology = %#v, want source order", occurrences.Occurrences)
}
var durable map[string]json.RawMessage
if err := json.Unmarshal(serialized.Artifact.Content, &durable); err != nil {
t.Fatalf("unmarshal durable occurrence payload: %v", err)
}
if len(durable) != 1 || durable["occurrences"] == nil {
t.Fatalf("durable occurrence payload = %#v, want only occurrences", durable)
}
}
func TestSemanticNPCNormalizationCrossesOrderedRegistryHandoff(t *testing.T) {
registries := productionNPCRegistries(t)
cfg := loadNPCOccurrencePipelineConfig(t)
profile := cfg.Pipelines["dnd-npc-occurrences-fixture"]
profile.Chunk = pipeline.ModuleBinding{Module: "generic", Options: map[string]any{"max_units": 1}}
cfg.Pipelines["dnd-npc-occurrences-fixture"] = profile
effective, err := cfg.Resolve(config.ResolveInput{PipelineID: "dnd-npc-occurrences-fixture", Catalog: moduleCatalog(registries)})
if err != nil {
t.Fatal(err)
}
resolved, warnings, err := pipeline.MaterializeReferences(effective.ResolvedPipeline, moduleCatalog(registries), pipeline.ReferenceMaterializationOptions{})
if err != nil || len(warnings) != 0 {
t.Fatalf("MaterializeReferences() error = %v warnings = %#v", err, warnings)
}
client := &semanticNPCOccurrenceClient{}
raw := []byte(`{"metadata":{"id":"semantic-session","title":"Semantic NPC session"},"segments":[{"id":1,"start":0,"end":1,"speaker":"DM","text":"Mira Thorn enters."},{"id":2,"start":1,"end":2,"speaker":"DM","text":"Mira Thorn, the Greencloak, waves."}]}`)
output, err := runPreparedPipeline(t, registries, resolved, client, pipeline.RunInput{RawInput: raw})
if err != nil {
t.Fatalf("Run() error = %v", err)
}
if client.requestCount(npcregistry.PromptID) != 2 || client.requestCount(npcnormalize.PromptID) != 1 {
t.Fatalf("prompt requests = %#v, want two extraction calls and one document normalization call", client.requests)
}
npcOutput := normalizedLane(t, output, "npc_registry")
npcsValue, err := npccodec.New().Decode(npcOutput.Artifact.Content)
if err != nil {
t.Fatal(err)
}
if npcOutput.StepID != "identify-npcs" || len(npcsValue.NPCs) != 1 || npcsValue.NPCs[0].Name != "Mira Thorn" || npcsValue.NPCs[0].ID != identity.DeriveID("Mira Thorn") {
t.Fatalf("NPC output = %#v / %#v, want canonical ordered producer artifact", npcOutput, npcsValue)
}
if refs := npcsValue.NPCs[0].SourceRefs; !reflect.DeepEqual(refs, []source.SourceRef{{SourceID: "semantic-session", StartUnitID: 1, EndUnitID: 1}, {SourceID: "semantic-session", StartUnitID: 2, EndUnitID: 2}}) {
t.Fatalf("NPC evidence = %#v, want original extraction evidence union", refs)
}
occurrenceOutput := normalizedLane(t, output, "occurrences")
if occurrenceOutput.StepID != "extract-occurrences" {
t.Fatalf("occurrence output step = %q, want ordered downstream step", occurrenceOutput.StepID)
}
registryRequest := client.requestFor(t, occurrenceextract.PromptID)
if got := string(registryRequest.Inputs["npc_registry"].Content); got != `{"npcs":[{"name":"Mira Thorn"}]}` {
t.Fatalf("downstream registry = %s, want one canonical NPC name", got)
}
manifestContent, err := json.Marshal(output.Manifest)
if err != nil {
t.Fatal(err)
}
for _, forbidden := range []string{"npc:sha256:", "Mira Thorn enters.", "Mira Thorn, the Greencloak, waves."} {
if strings.Contains(string(manifestContent), forbidden) {
t.Fatalf("manifest leaked private identity or transcript content %q: %s", forbidden, manifestContent)
}
}
}
func TestNPCOccurrencePipelineSkipsConsumerWhenNPCProducerIsRejected(t *testing.T) {
registries := productionNPCRegistries(t)
resolved := resolveNPCOccurrencePipeline(t, registries)
client := &npcOccurrenceLLMClient{rejectNPCs: true}
output, err := runPreparedPipeline(t, registries, resolved, client, pipeline.RunInput{RawInput: readNPCFixture(t)})
if err == nil {
t.Fatalf("Run() output = %#v, want missing generated NPC producer error", output)
}
if client.requestCount(npcregistry.PromptID) != 1 {
t.Fatalf("NPC requests = %d, want rejected producer", client.requestCount(npcregistry.PromptID))
}
if client.requestCount(occurrenceextract.PromptID) != 0 {
t.Fatalf("occurrence requests = %d, want none after rejected producer", client.requestCount(occurrenceextract.PromptID))
}
}
func resolveNPCOccurrencePipeline(t *testing.T, registries pipeline.Registries) pipeline.ResolvedPipeline {
t.Helper()
configValue := loadNPCOccurrencePipelineConfig(t)
effective, err := configValue.Resolve(config.ResolveInput{PipelineID: "dnd-npc-occurrences-fixture", Catalog: moduleCatalog(registries)})
if err != nil {
t.Fatalf("Resolve() error = %v", err)
}
resolved, warnings, err := pipeline.MaterializeReferences(effective.ResolvedPipeline, moduleCatalog(registries), pipeline.ReferenceMaterializationOptions{})
if err != nil || len(warnings) != 0 {
t.Fatalf("MaterializeReferences() error = %v warnings = %#v", err, warnings)
}
return resolved
}
func loadNPCOccurrencePipelineConfig(t *testing.T) config.Config {
t.Helper()
data, err := os.ReadFile("testdata/dnd_npc_occurrences_pipeline.yml")
if err != nil {
t.Fatalf("ReadFile(dnd_npc_occurrences_pipeline.yml) error = %v", err)
}
fileConfig, err := config.ParseFileConfigYAML(data)
if err != nil {
t.Fatalf("ParseFileConfigYAML() error = %v", err)
}
result := config.Default()
if err := result.ApplyFileConfig(fileConfig); err != nil {
t.Fatalf("ApplyFileConfig() error = %v", err)
}
return result
}
func normalizedLane(t *testing.T, output pipeline.RunOutput, laneID string) contracts.SerializedOutput {
t.Helper()
for _, serialized := range output.NormalizeOutputs {
if serialized.LaneID == laneID {
return serialized
}
}
t.Fatalf("normalized lanes = %#v, missing %q", output.NormalizeOutputs, laneID)
return contracts.SerializedOutput{}
}
func assertOccurrenceEvidence(t *testing.T, references []source.SourceRef) {
t.Helper()
if len(references) == 0 {
t.Fatal("occurrence has no current-source evidence")
}
for _, reference := range references {
if reference.SourceID != "npc-session" {
t.Fatalf("occurrence evidence = %#v, want current source only", reference)
}
}
}
type npcOccurrenceLLMClient struct {
mu sync.Mutex
requests []contracts.StructuredCompletionRequest
rejectNPCs bool
}
func (client *npcOccurrenceLLMClient) CompleteStructured(ctx context.Context, request contracts.StructuredCompletionRequest, out any) (contracts.StructuredCompletionResponse, error) {
if err := ctx.Err(); err != nil {
return contracts.StructuredCompletionResponse{}, err
}
client.mu.Lock()
client.requests = append(client.requests, cloneStructuredCompletionRequest(request))
client.mu.Unlock()
var payload any
switch request.PromptID {
case npcregistry.PromptID:
if client.rejectNPCs {
payload = map[string]any{"npcs": []any{map[string]any{
"name": "", "source_refs": []any{map[string]int{"start_unit_id": 1, "end_unit_id": 1}},
}}}
} else {
payload = map[string]any{"npcs": []any{
map[string]any{"name": "Mira Thorn", "source_refs": []any{map[string]int{"start_unit_id": 1, "end_unit_id": 1}}},
map[string]any{"name": "Hooded Guard", "source_refs": []any{map[string]int{"start_unit_id": 3, "end_unit_id": 3}}},
}}
}
case npcnormalize.PromptID:
payload = map[string]any{"duplicate_groups": []any{}}
case occurrenceextract.PromptID:
payload = map[string]any{"occurrences": []any{
map[string]any{"npc_id": identity.DeriveID("Hooded Guard"), "name": "Hooded Guard", "kind": "noncombat_presence", "source_refs": []any{map[string]int{"start_unit_id": 3, "end_unit_id": 3}}},
map[string]any{"npc_id": identity.DeriveID("Mira Thorn"), "name": "Mira Thorn", "kind": "dialogue", "source_refs": []any{map[string]int{"start_unit_id": 2, "end_unit_id": 2}}},
}}
default:
return contracts.StructuredCompletionResponse{}, fmt.Errorf("unexpected occurrence prompt %q", request.PromptID)
}
content, err := json.Marshal(payload)
if err != nil {
return contracts.StructuredCompletionResponse{}, err
}
if err := json.Unmarshal(content, out); err != nil {
return contracts.StructuredCompletionResponse{}, fmt.Errorf("populate occurrence response: %w", err)
}
return contracts.StructuredCompletionResponse{Content: content, Provider: "test", Model: "occurrence-fake"}, nil
}
func (client *npcOccurrenceLLMClient) requestFor(t *testing.T, promptID string) contracts.StructuredCompletionRequest {
t.Helper()
client.mu.Lock()
defer client.mu.Unlock()
for _, request := range client.requests {
if request.PromptID == promptID {
return request
}
}
t.Fatalf("requests = %#v, missing prompt %q", client.requests, promptID)
return contracts.StructuredCompletionRequest{}
}
func (client *npcOccurrenceLLMClient) requestCount(promptID string) int {
client.mu.Lock()
defer client.mu.Unlock()
count := 0
for _, request := range client.requests {
if request.PromptID == promptID {
count++
}
}
return count
}
var _ contracts.StructuredLLMClient = (*npcOccurrenceLLMClient)(nil)
type semanticNPCOccurrenceClient struct {
requests []contracts.StructuredCompletionRequest
npcCalls int
}
func (client *semanticNPCOccurrenceClient) CompleteStructured(_ context.Context, request contracts.StructuredCompletionRequest, out any) (contracts.StructuredCompletionResponse, error) {
client.requests = append(client.requests, cloneStructuredCompletionRequest(request))
var payload any
switch request.PromptID {
case npcregistry.PromptID:
client.npcCalls++
name := "Mira Thorn"
if client.npcCalls == 2 {
name = "Mira Thorn, the Greencloak"
}
payload = map[string]any{"npcs": []any{map[string]any{"name": name, "source_refs": []any{map[string]int{"start_unit_id": client.npcCalls, "end_unit_id": client.npcCalls}}}}}
case npcnormalize.PromptID:
content, err := contextualReconciliationContent([]byte(`{"duplicate_groups":[{"members":["candidate-000001","candidate-000002"],"canonical":"candidate-000001"}]}`), request.Inputs["candidates"].Content)
if err != nil {
return contracts.StructuredCompletionResponse{}, err
}
if err := json.Unmarshal(content, out); err != nil {
return contracts.StructuredCompletionResponse{}, err
}
return contracts.StructuredCompletionResponse{Content: content}, nil
case occurrenceextract.PromptID:
payload = map[string]any{"occurrences": []any{map[string]any{"npc_id": identity.DeriveID("Mira Thorn"), "name": "Mira Thorn", "kind": "dialogue", "source_refs": []any{map[string]int{"start_unit_id": 1, "end_unit_id": 1}}}}}
default:
return contracts.StructuredCompletionResponse{}, fmt.Errorf("unexpected semantic pipeline prompt %q", request.PromptID)
}
content, err := json.Marshal(payload)
if err != nil {
return contracts.StructuredCompletionResponse{}, err
}
if err := json.Unmarshal(content, out); err != nil {
return contracts.StructuredCompletionResponse{}, err
}
return contracts.StructuredCompletionResponse{Content: content}, nil
}
func (client *semanticNPCOccurrenceClient) requestCount(promptID string) int {
count := 0
for _, request := range client.requests {
if request.PromptID == promptID {
count++
}
}
return count
}
func (client *semanticNPCOccurrenceClient) requestFor(t *testing.T, promptID string) contracts.StructuredCompletionRequest {
t.Helper()
for _, request := range client.requests {
if request.PromptID == promptID {
return request
}
}
t.Fatalf("requests = %#v, missing %q", client.requests, promptID)
return contracts.StructuredCompletionRequest{}
}
var _ contracts.StructuredLLMClient = (*semanticNPCOccurrenceClient)(nil)