Integrate NPC semantic normalization

This commit is contained in:
2026-07-26 01:41:35 +00:00
parent d1c48db4bc
commit 8d9a496935
4 changed files with 234 additions and 16 deletions

View File

@@ -32,6 +32,20 @@ func TestRegisterAddsDNDFamily(t *testing.T) {
if err := Register(registries, assets); err != nil {
t.Fatalf("Register() error = %v, want nil", err)
}
promptFS, err := assets.PromptFS()
if err != nil {
t.Fatalf("PromptFS() error = %v", err)
}
if _, err := fs.ReadFile(promptFS, "dnd.npcs.normalize/dnd.npcs.normalize.yaml"); err != nil {
t.Fatalf("normalization prompt asset = %v, want registered private prompt", err)
}
schemaFS, err := assets.SchemaFS()
if err != nil {
t.Fatalf("SchemaFS() error = %v", err)
}
if _, err := fs.ReadFile(schemaFS, "dnd_npcs_normalize_llm.v1.json"); err != nil {
t.Fatalf("normalization schema asset = %v, want registered private schema", err)
}
assertContainsKeys(t, "chunkers", registries.Chunkers.RegisteredKeys(), []string{"dnd/scenes"})
assertContainsKeys(t, "extractors", registries.Extractors.RegisteredKeys(), []string{"dnd/spells", npcextract.Key, combatextract.Key, itemeventextract.Key, interactionextract.Key, scenedescriptionextract.Key})
assertContainsKeys(t, "normalizers", registries.Normalizers.RegisteredKeys(), []string{spellnormalize.Key, npcnormalize.Key, combatnormalize.Key, itemeventnormalize.Key, interactionnormalize.Key, scenedescriptionnormalize.Key, pipeline.DefaultNormalizeModule})

View File

@@ -24,6 +24,7 @@ import (
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/npcs"
sceneextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/scenedescriptions"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/spells"
npcnormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/npcs"
)
func TestNPCOutputGroundsSpellAndCombatConsumersThroughOneOperation(t *testing.T) {
@@ -47,6 +48,9 @@ func TestNPCOutputGroundsSpellAndCombatConsumersThroughOneOperation(t *testing.T
}
for name, value := range map[string]string{
"extract:npcs:dnd/npcs:mapping_policy": "dnd.npcs.extract_mapping.v2",
"normalize:npcs:dnd/npcs:identity_policy": "dnd.npcs.identity.v1",
"normalize:npcs:dnd/npcs:normalization_policy": "dnd.npcs.normalize.v3",
"normalize:npcs:dnd/npcs:semantic_context_policy": "dnd.npcs.semantic_context.v1:2",
"extract:spells:dnd/spells:mapping_policy": "dnd.spells.extract_mapping.v2",
"extract:combat:dnd/combat-turns:scene_gate_policy": "dnd.combat_turns.scene_gate.v1",
} {
@@ -55,6 +59,8 @@ func TestNPCOutputGroundsSpellAndCombatConsumersThroughOneOperation(t *testing.T
for _, name := range []string{
"extract:npcs:dnd/npcs:prompt",
"extract:npcs:dnd/npcs:response_schema",
"normalize:npcs:dnd/npcs:prompt",
"normalize:npcs:dnd/npcs:response_schema",
"extract:spells:dnd/spells:prompt",
"extract:spells:dnd/spells:response_schema",
"extract:spells:dnd/spells:npc_registry",
@@ -455,6 +461,8 @@ func (client *groundedDNDLLMClient) CompleteStructured(ctx context.Context, requ
"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 sceneextract.PromptID:
kind := client.sceneKind
if kind == "" {

View File

@@ -5,6 +5,8 @@ import (
"encoding/json"
"fmt"
"os"
"reflect"
"strings"
"sync"
"testing"
@@ -16,6 +18,8 @@ import (
npccodec "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/codec/npcs"
interactionextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/npcinteractions"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/npcs"
npcnormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/npcs"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/npcs/identity"
)
func TestNPCInteractionPipelineUsesAcceptedRegistryAndCurrentEvidence(t *testing.T) {
@@ -70,6 +74,59 @@ func TestNPCInteractionPipelineUsesAcceptedRegistryAndCurrentEvidence(t *testing
}
}
func TestSemanticNPCNormalizationCrossesOrderedRegistryHandoff(t *testing.T) {
registries := productionNPCRegistries(t)
cfg := loadNPCInteractionPipelineConfig(t)
profile := cfg.Pipelines["dnd-npc-interactions-fixture"]
profile.Chunk = pipeline.ModuleBinding{Module: "generic", Options: map[string]any{"max_units": 1}}
cfg.Pipelines["dnd-npc-interactions-fixture"] = profile
effective, err := cfg.Resolve(config.ResolveInput{PipelineID: "dnd-npc-interactions-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 := &semanticNPCInteractionClient{}
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(npcs.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, "npcs")
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)
}
interactionOutput := normalizedLane(t, output, "interactions")
if interactionOutput.StepID != "extract-interactions" {
t.Fatalf("interaction output step = %q, want ordered downstream step", interactionOutput.StepID)
}
registryRequest := client.requestFor(t, interactionextract.PromptID)
if got := string(registryRequest.Inputs["npcs"].Content); got != `{"npcs":[{"name":"Mira Thorn"}]}` {
t.Fatalf("downstream registry = %s, want one canonical names-only NPC", 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 TestNPCInteractionPipelineSkipsConsumerWhenNPCProducerIsRejected(t *testing.T) {
registries := productionNPCRegistries(t)
resolved := resolveNPCInteractionPipeline(t, registries)
@@ -168,6 +225,8 @@ func (client *npcInteractionLLMClient) CompleteStructured(ctx context.Context, r
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 interactionextract.PromptID:
payload = map[string]any{"interactions": []any{
map[string]any{"name": "Hooded Guard", "kind": "noncombat_presence", "source_refs": []any{map[string]int{"start_unit_id": 3, "end_unit_id": 3}}},
@@ -212,3 +271,59 @@ func (client *npcInteractionLLMClient) requestCount(promptID string) int {
}
var _ contracts.StructuredLLMClient = (*npcInteractionLLMClient)(nil)
type semanticNPCInteractionClient struct {
requests []contracts.StructuredCompletionRequest
npcCalls int
}
func (client *semanticNPCInteractionClient) 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 npcs.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:
payload = map[string]any{"duplicate_groups": []any{map[string]any{"members": []string{"Mira Thorn", "Mira Thorn, the Greencloak"}, "canonical_name": "Mira Thorn"}}}
case interactionextract.PromptID:
payload = map[string]any{"interactions": []any{map[string]any{"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 *semanticNPCInteractionClient) requestCount(promptID string) int {
count := 0
for _, request := range client.requests {
if request.PromptID == promptID {
count++
}
}
return count
}
func (client *semanticNPCInteractionClient) 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 = (*semanticNPCInteractionClient)(nil)

View File

@@ -14,6 +14,7 @@ import (
"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
npccodec "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/codec/npcs"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/npcs"
npcnormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/npcs"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/npcs/identity"
dndregister "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/register"
npcshape "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/npcs/shape"
@@ -95,7 +96,7 @@ func TestRunnerProcessesSeriatimInputWithProductionDNDNPCPipeline(t *testing.T)
t.Fatalf("manifest lane = %#v, want NPC production composition", lane)
}
normalizerMetadata, ok := lane.Metadata["normalizer"].(map[string]any)
if !ok || normalizerMetadata["identity_policy"] != identity.Policy || normalizerMetadata["normalization_policy"] != "dnd.npcs.normalize.v2" {
if !ok || normalizerMetadata["identity_policy"] != identity.Policy || normalizerMetadata["normalization_policy"] != npcnormalize.NormalizationPolicy || normalizerMetadata["prompt_id"] != npcnormalize.PromptID || normalizerMetadata["response_schema_id"] != npcnormalize.ResponseSchemaID {
t.Fatalf("normalizer metadata = %#v, want identity and normalization policies", lane.Metadata)
}
var npcOutputFile *contracts.OutputFile
@@ -108,8 +109,8 @@ func TestRunnerProcessesSeriatimInputWithProductionDNDNPCPipeline(t *testing.T)
if npcOutputFile == nil || npcOutputFile.ContentType != npccodec.MediaType {
t.Fatalf("output files = %#v, want JSON NPC lane file", output.OutputFiles)
}
if len(client.requests) != 1 || client.requests[0].PromptID != npcs.PromptID {
t.Fatalf("LLM requests = %#v, want one NPC prompt request", client.requests)
if len(client.requests) != 2 || client.requests[0].PromptID != npcs.PromptID || client.requests[1].PromptID != npcnormalize.PromptID {
t.Fatalf("LLM requests = %#v, want extraction and normalization prompt requests", client.requests)
}
}
@@ -170,6 +171,52 @@ func TestProductionNPCPipelineRoutesSemanticCandidatesToDeterministicValidators(
}
}
func TestProductionNPCNormalizationRetryUsesFinalSafeProposal(t *testing.T) {
registries := productionNPCRegistries(t)
baseResponse := npcProductionResponse{NPCs: []npcProductionRecord{
{Name: "Mira", SourceRefs: []npcProductionSourceRef{{StartUnitID: 1, EndUnitID: 1}}},
{Name: "Mira Thorn", SourceRefs: []npcProductionSourceRef{{StartUnitID: 2, EndUnitID: 2}}},
{Name: "Hooded Guard", SourceRefs: []npcProductionSourceRef{{StartUnitID: 3, EndUnitID: 3}}},
}}
partial := []byte(`{"duplicate_groups":[{"members":["Mira","Mira Thorn"],"canonical_name":"Mira Thorn"},{"members":["Hooded Guard","Unknown"],"canonical_name":"Hooded Guard"}]}`)
safe := []byte(`{"duplicate_groups":[{"members":["Mira","Mira Thorn"],"canonical_name":"Mira Thorn"}]}`)
for _, test := range []struct {
name string
retries int
responses [][]byte
wantCalls int
wantExhaustion bool
}{
{name: "default retry budget", responses: [][]byte{partial}, wantCalls: 1, wantExhaustion: true},
{name: "later complete proposal", retries: 1, responses: [][]byte{partial, safe}, wantCalls: 2},
} {
t.Run(test.name, func(t *testing.T) {
cfg := loadNPCPipelineConfig(t)
profile := cfg.Pipelines["dnd-npcs-fixture"]
lane := profile.Artifacts["npcs"]
lane.Normalize.Retries = test.retries
profile.Artifacts["npcs"] = lane
cfg.Pipelines["dnd-npcs-fixture"] = profile
effective, err := cfg.Resolve(config.ResolveInput{PipelineID: "dnd-npcs-fixture", Catalog: moduleCatalog(registries)})
if err != nil {
t.Fatal(err)
}
client := &fakeNPCProductionLLMClient{response: baseResponse, normalizeResponses: test.responses}
output, err := runPreparedPipeline(t, registries, effective.ResolvedPipeline, client, pipeline.RunInput{RawInput: readNPCFixture(t)})
if err != nil {
t.Fatalf("Run() error = %v", err)
}
if client.requestCount(npcnormalize.PromptID) != test.wantCalls || len(output.NormalizeOutputs) != 1 {
t.Fatalf("normalization calls = %d output = %#v, want %d accepted result", client.requestCount(npcnormalize.PromptID), output.NormalizeOutputs, test.wantCalls)
}
if got := hasWarningReason(output.Warnings, npcnormalize.ReasonCodeNPCSemanticReconciliationExhausted); got != test.wantExhaustion {
t.Fatalf("warnings = %#v, exhaustion = %t, want %t", output.Warnings, got, test.wantExhaustion)
}
})
}
}
type npcProductionResponse struct {
NPCs []npcProductionRecord `json:"npcs"`
}
@@ -185,26 +232,41 @@ type npcProductionSourceRef struct {
}
type fakeNPCProductionLLMClient struct {
response npcProductionResponse
rawResponses [][]byte
requests []contracts.StructuredCompletionRequest
response npcProductionResponse
rawResponses [][]byte
normalizeResponses [][]byte
requests []contracts.StructuredCompletionRequest
}
func (client *fakeNPCProductionLLMClient) CompleteStructured(_ context.Context, req contracts.StructuredCompletionRequest, out any) (contracts.StructuredCompletionResponse, error) {
client.requests = append(client.requests, req)
var content []byte
if client.rawResponses != nil {
index := len(client.requests) - 1
if index >= len(client.rawResponses) {
return contracts.StructuredCompletionResponse{}, fmt.Errorf("missing fake NPC response %d", index)
switch req.PromptID {
case npcs.PromptID:
if client.rawResponses != nil {
index := client.requestCount(npcs.PromptID) - 1
if index >= len(client.rawResponses) {
return contracts.StructuredCompletionResponse{}, fmt.Errorf("missing fake NPC response %d", index)
}
content = append([]byte(nil), client.rawResponses[index]...)
} else {
var err error
content, err = json.Marshal(client.response)
if err != nil {
return contracts.StructuredCompletionResponse{}, err
}
}
content = append([]byte(nil), client.rawResponses[index]...)
} else {
var err error
content, err = json.Marshal(client.response)
if err != nil {
return contracts.StructuredCompletionResponse{}, err
case npcnormalize.PromptID:
content = []byte(`{"duplicate_groups":[]}`)
if client.normalizeResponses != nil {
index := client.requestCount(npcnormalize.PromptID) - 1
if index >= len(client.normalizeResponses) {
return contracts.StructuredCompletionResponse{}, fmt.Errorf("missing fake NPC normalization response %d", index)
}
content = append([]byte(nil), client.normalizeResponses[index]...)
}
default:
return contracts.StructuredCompletionResponse{}, fmt.Errorf("unexpected fake NPC prompt %q", req.PromptID)
}
if err := json.Unmarshal(content, out); err != nil {
return contracts.StructuredCompletionResponse{}, fmt.Errorf("populate NPC structured target: %w", err)
@@ -212,6 +274,16 @@ func (client *fakeNPCProductionLLMClient) CompleteStructured(_ context.Context,
return contracts.StructuredCompletionResponse{Content: content}, nil
}
func (client *fakeNPCProductionLLMClient) requestCount(promptID string) int {
count := 0
for _, request := range client.requests {
if request.PromptID == promptID {
count++
}
}
return count
}
func productionNPCRegistries(t *testing.T) pipeline.Registries {
t.Helper()
registries := pipeline.Registries{
@@ -283,3 +355,12 @@ func hasNPCWarning(warnings []contracts.Warning, reason string) bool {
}
return false
}
func hasWarningReason(warnings []contracts.Warning, reason string) bool {
for _, warning := range warnings {
if warning.ReasonCode == reason {
return true
}
}
return false
}