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

211 lines
7.9 KiB
Go

package integration_test
import (
"context"
"crypto/sha256"
"encoding/json"
"fmt"
"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"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd"
combatcodec "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/codec/combatturns"
npccodec "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/codec/npcs"
combatextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/combatturns"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/npcs"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/spells"
)
func TestNPCOutputGroundsSpellAndCombatConsumersThroughOneOperation(t *testing.T) {
registries := productionNPCRegistries(t)
catalog := moduleCatalog(registries)
configValue := loadGroundedPipelineConfig(t)
effective, err := configValue.Resolve(config.ResolveInput{PipelineID: "dnd-npc-grounded", Catalog: catalog})
if err != nil {
t.Fatalf("Resolve() error = %v", err)
}
materialized, warnings, err := pipeline.MaterializeReferences(effective.ResolvedPipeline, catalog, pipeline.ReferenceMaterializationOptions{})
if err != nil || len(warnings) != 0 {
t.Fatalf("MaterializeReferences() error = %v warnings = %#v", err, warnings)
}
client := &groundedDNDLLMClient{}
output, err := runPreparedPipeline(t, registries, materialized, client, pipeline.RunInput{
RawInput: readNPCFixture(t),
ExtractWorkers: 1,
})
if err != nil {
t.Fatalf("Run() error = %v", err)
}
if len(output.Rejected) != 0 || len(output.NormalizeOutputs) != 3 {
t.Fatalf("run outputs = %#v rejected = %#v, want NPC, spell, and combat outputs", output.NormalizeOutputs, output.Rejected)
}
var npcPayload []byte
for _, serialized := range output.NormalizeOutputs {
if serialized.LaneID == "npcs" {
npcPayload = append([]byte(nil), serialized.Artifact.Content...)
break
}
}
if len(npcPayload) == 0 {
t.Fatal("NPC producer did not publish a canonical payload")
}
npcValue, err := npccodec.New().Decode(npcPayload)
if err != nil {
t.Fatalf("decode NPC producer payload: %v", err)
}
npcPayload, err = npccodec.New().Encode(npcValue)
if err != nil {
t.Fatalf("encode canonical NPC producer payload: %v", err)
}
canonicalDigest := digestBytes(npcPayload)
projection := []byte(`{"npcs":[{"name":"Mira Thorn"},{"name":"Hooded Guard"}]}`)
projectionDigest := digestBytes(projection)
seenConsumers := map[string]bool{}
for _, request := range client.requestsSnapshot() {
if request.PromptID != spells.PromptID && request.PromptID != combatextract.PromptID {
continue
}
input := request.Inputs["npcs"]
if input.MediaType != npccodec.MediaType || input.Digest != projectionDigest || string(input.Content) != string(projection) || input.OriginURI != "" {
t.Fatalf("%s NPC prompt input = %#v, want names-only generated registry", request.PromptID, input)
}
seenConsumers[request.PromptID] = true
}
if !seenConsumers[spells.PromptID] || !seenConsumers[combatextract.PromptID] {
t.Fatalf("consumer prompt IDs = %#v, want spell and combat requests", seenConsumers)
}
provenanceCount := 0
for _, reference := range output.Manifest.References {
if reference.SlotName != "npcs" {
continue
}
provenanceCount++
if reference.Digest != canonicalDigest || reference.OriginType != "generated" {
t.Fatalf("NPC generated provenance = %#v, want canonical digest and generated origin", reference)
}
}
if provenanceCount != 3 {
t.Fatalf("NPC generated provenance count = %d, want spell extract plus combat extract/normalize", provenanceCount)
}
for _, lane := range output.Manifest.ArtifactLanes {
for _, component := range []string{"extractor", "normalizer"} {
metadata, ok := lane.Metadata[component].(map[string]any)
if ok && metadata["npc_registry_digest"] != nil {
t.Fatalf("%s %s metadata = %#v, want generated identity only in framework provenance", lane.ID, component, metadata)
}
}
}
var combatValue dnd.CombatTurnList
for _, serialized := range output.NormalizeOutputs {
switch serialized.LaneID {
case "spells":
spellValue := decodeRunnerSpellResponse(t, serialized.Artifact.Content)
if len(spellValue.SpellCasts) != 1 || spellValue.SpellCasts[0].Caster != "Mira Thorn" {
t.Fatalf("spell output = %#v, want one registry-grounded-context spell", spellValue)
}
assertCurrentEvidence(t, spellValue.SpellCasts[0].SourceRefs)
case "combat":
decoded, decodeErr := combatcodec.New().Decode(serialized.Artifact.Content)
if decodeErr != nil {
t.Fatalf("decode combat output: %v", decodeErr)
}
combatValue = decoded
}
}
if len(combatValue.CombatTurns) != 1 || combatValue.CombatTurns[0].Actor != "Mira Thorn" {
t.Fatalf("combat output = %#v, want registry-normalized actor", combatValue)
}
assertCurrentEvidence(t, combatValue.CombatTurns[0].SourceRefs)
}
func assertCurrentEvidence(t *testing.T, references []source.SourceRef) {
t.Helper()
for _, reference := range references {
if reference.SourceID != "npc-session" {
t.Fatalf("evidence reference = %#v, want current source only", reference)
}
}
}
func loadGroundedPipelineConfig(t *testing.T) config.Config {
t.Helper()
fileConfig, err := config.LoadFileConfig(repositoryPathForIntegration("internal", "modules", "integration", "testdata", "dnd_npc_grounded_pipeline.yml"))
if err != nil {
t.Fatalf("LoadFileConfig() error = %v", err)
}
cfg := config.Default()
if err := cfg.ApplyFileConfig(fileConfig); err != nil {
t.Fatalf("ApplyFileConfig() error = %v", err)
}
return cfg
}
type groundedDNDLLMClient struct {
mu sync.Mutex
requests []contracts.StructuredCompletionRequest
}
func (client *groundedDNDLLMClient) 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 npcs.PromptID:
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 spells.PromptID:
payload = map[string]any{"spell_casts": []any{map[string]any{
"caster": "Mira Thorn", "spell": "Cure Wounds",
"source_refs": []any{map[string]int{"start_unit_id": 1, "end_unit_id": 1}},
}}}
case combatextract.PromptID:
payload = map[string]any{"combat_turns": []any{map[string]any{
"actor": "Mira Thorn",
"turn_kind": "turn",
"source_refs": []any{map[string]int{"start_unit_id": 1, "end_unit_id": 1}},
}}}
default:
return contracts.StructuredCompletionResponse{}, fmt.Errorf("unexpected grounded 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 grounded response: %w", err)
}
return contracts.StructuredCompletionResponse{Content: content, Provider: "test", Model: "grounded-fake"}, nil
}
func (client *groundedDNDLLMClient) requestsSnapshot() []contracts.StructuredCompletionRequest {
client.mu.Lock()
defer client.mu.Unlock()
return append([]contracts.StructuredCompletionRequest(nil), client.requests...)
}
func digestBytes(content []byte) string {
sum := sha256.Sum256(content)
return fmt.Sprintf("sha256:%x", sum[:])
}
var _ contracts.StructuredLLMClient = (*groundedDNDLLMClient)(nil)