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

@@ -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)