Files
notarius/internal/cli/dnd_enemy_events_contract_test.go

276 lines
13 KiB
Go

package cli
import (
"context"
"encoding/json"
"errors"
"fmt"
"os"
"path/filepath"
"reflect"
"strings"
"sync"
"testing"
"time"
"gitea.maximumdirect.net/eric/notarius/internal/core/artifacts"
"gitea.maximumdirect.net/eric/notarius/internal/core/config"
"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
"gitea.maximumdirect.net/eric/notarius/internal/framework/evidencecontext"
"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/chunk/scenes"
combat "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/combatturns"
enemyevents "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/enemyevents"
itemevents "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/itemevents"
npcinteractions "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/npcinteractions"
npcs "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/npcs"
scenedescriptions "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/scenedescriptions"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/spells"
enemyeventnormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/enemyevents"
npcnormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/npcs"
)
func TestProductionEnemyEventConfigurationResolvesGeneratedHandoffs(t *testing.T) {
components := productionTestComponents(t)
cfg := loadMaintainedExample(t, repositoryPath("examples", "dnd-complete.config.yml"))
effective, err := cfg.Resolve(resolveInputForMaintainedExample(components, "dnd-session"))
if err != nil {
t.Fatalf("Resolve() error = %v, want nil", err)
}
materialized, _, err := pipeline.MaterializeReferences(effective.ResolvedPipeline, catalogFromRegistries(components.registries), pipeline.ReferenceMaterializationOptions{
ConfigPath: repositoryPath("examples", "dnd-complete.config.yml"),
WorkingDir: repositoryPath("examples"),
})
if err != nil {
t.Fatalf("MaterializeReferences() error = %v, want nil", err)
}
lane := referenceContractLane(t, materialized, "enemy-events")
if lane.ArtifactKind != dnd.EnemyEventListKind || lane.Extract.Module != enemyevents.Key || lane.Extract.Retries != 2 || lane.Merge.Module != pipeline.DefaultMergeModule || lane.Normalize.Module != enemyeventnormalize.Key {
t.Fatalf("enemy event lane = %#v, want typed production composition", lane)
}
for slot, want := range map[string]struct{ step, lane string }{
"npcs": {step: "describe-session", lane: "npcs"},
"scene_descriptions": {step: "describe-session", lane: "scene-descriptions"},
"combat_turns": {step: "extract-events", lane: "combat-turns"},
"npc_interactions": {step: "extract-events", lane: "npc-interactions"},
} {
binding, found := generatedReferenceBinding(lane.ExtractReferences.Bindings, slot)
if !found || binding.Artifact.Step != want.step || binding.Artifact.Lane != want.lane {
t.Fatalf("enemy event %s reference = %#v, want generated %s/%s artifact", slot, binding, want.step, want.lane)
}
}
if binding, found := generatedReferenceBinding(lane.NormalizeReferences.Bindings, "npcs"); !found || binding.Artifact.Step != "describe-session" || binding.Artifact.Lane != "npcs" {
t.Fatalf("enemy event normalizer NPC reference = %#v, want generated NPC artifact", binding)
}
catalog := catalogFromRegistries(components.registries)
extractSpec, ok := catalog.Extractors.Spec(enemyevents.Key)
if !ok || !reflect.DeepEqual(extractSpec.Requires, []string{"chunks", "source.transcript"}) || !reflect.DeepEqual(extractSpec.Provides, []string{"dnd.enemy_events"}) {
t.Fatalf("enemy event extractor spec = %#v, want source and artifact capabilities", extractSpec)
}
normalizeSpec, ok := catalog.Normalizers.SpecForArtifact(enemyeventnormalize.Key, dnd.EnemyEventListKind)
if !ok || !reflect.DeepEqual(normalizeSpec.Requires, []string{"merged"}) || !reflect.DeepEqual(normalizeSpec.Provides, []string{"normalized"}) {
t.Fatalf("enemy event normalizer spec = %#v, want merged/normalized capabilities", normalizeSpec)
}
for _, slot := range []string{"npcs", "scene_descriptions", "combat_turns", "npc_interactions"} {
if !hasReferenceSlot(extractSpec.ReferenceSlots, slot) {
t.Fatalf("enemy event extractor slots = %#v, want %q", extractSpec.ReferenceSlots, slot)
}
}
if !hasReferenceSlot(normalizeSpec.ReferenceSlots, "npcs") {
t.Fatalf("enemy event normalizer slots = %#v, want NPC registry", normalizeSpec.ReferenceSlots)
}
profile := cfg.Pipelines["dnd-session"]
profile.Steps[2].References["npcs"] = pipeline.GeneratedReference("track-enemies", "enemy-events")
cfg.Pipelines["dnd-session"] = profile
if _, err := cfg.Resolve(resolveInputForMaintainedExample(components, "dnd-session")); err == nil || !strings.Contains(err.Error(), "earlier step") {
t.Fatalf("Resolve() error = %v, want future generated-reference rejection", err)
}
}
func TestMaintainedCompleteExampleProducesEnemyEventsThroughGeneratedHandoffs(t *testing.T) {
t.Chdir(repositoryPath())
outputRoot := filepath.Join(t.TempDir(), "output")
configPath := completeExampleConfigWithTemporaryCache(t)
client := &enemyEventLLMClient{}
options := productionCLIOptions(t)
options.Now = func() time.Time { return time.Unix(1700000000, 0).UTC() }
options.RunIDGenerator = func(time.Time) (string, error) { return productionRunID, nil }
options.UserCacheDir = func() (string, error) { return "", errors.New("user cache must not be used") }
options.LLMClientFactory = func(context.Context, config.Config, string, LLMRuntimeOverrides) (contracts.StructuredLLMClient, []artifacts.LLMProfileManifest, error) {
return client, nil, nil
}
var stdout, stderr strings.Builder
code := RunWithOptions([]string{
"run", "dnd-session",
"--config", configPath,
"--input", repositoryPath("examples", "dnd-complete-transcript.json"),
"--chunk_cache", "bypass", "--output-dir", outputRoot, "--session-id", "enemy-event-session",
}, &stdout, &stderr, options)
if code != 0 {
t.Fatalf("code=%d stdout=%q stderr=%q", code, stdout.String(), stderr.String())
}
runRoot := filepath.Join(outputRoot, productionRunID)
index := readProductionJSON[exampleOutputIndex](t, filepath.Join(runRoot, "index.json"))
var enemyOutput exampleOutputIndexEntry
for _, entry := range index.OutputFiles {
if entry.LaneID == "enemy-events" {
enemyOutput = entry
break
}
}
if enemyOutput.File != "lanes/enemy-events.json" || enemyOutput.SchemaID != "notarius.dnd.enemy_events" || enemyOutput.SchemaVersion != "v1" {
t.Fatalf("enemy event output = %#v, want typed enemy-event JSON", enemyOutput)
}
value := readProductionJSON[dnd.EnemyEventList](t, filepath.Join(runRoot, enemyOutput.File))
if len(value.Events) != 1 || value.Events[0].Name != "Kesh" || value.Events[0].Kind != dnd.EnemyEventKindFled || len(value.Events[0].SourceRefs) != 1 || value.Events[0].SourceRefs[0].SourceID != "session-ravenfall" || value.Events[0].SourceRefs[0].StartUnitID != 10 {
t.Fatalf("enemy event artifact = %#v, want source-linked Kesh fleeing event", value)
}
evidence := readProductionJSON[evidencecontext.Document](t, filepath.Join(runRoot, "evidence-context.json"))
if !containsString(evidence.SelectedLanes, "enemy-events") || !evidenceHasLane(evidence, "enemy-events") {
t.Fatalf("evidence context = %#v, want direct enemy-event evidence", evidence)
}
requests := client.requestsFor(enemyevents.PromptID)
if len(requests) != 1 {
t.Fatalf("enemy event requests = %#v, want only the combat scene request", requests)
}
request := requests[0]
if request.SessionID != "enemy-event-session" {
t.Fatalf("enemy event session = %q, want shared session", request.SessionID)
}
for slot, required := range map[string]string{
"npcs": "Kesh",
"combat_turns": "Kesh",
"npc_interactions": "Kesh",
} {
input, ok := request.Inputs[slot]
if !ok || !strings.Contains(string(input.Content), required) || strings.Contains(string(input.Content), "source_refs") || strings.Contains(string(input.Content), "start_unit_id") {
t.Fatalf("enemy event %s prompt input = %q, want compact source-free grounding", slot, input.Content)
}
}
}
func completeExampleConfigWithTemporaryCache(t *testing.T) string {
t.Helper()
content, err := os.ReadFile(repositoryPath("examples", "dnd-complete.config.yml"))
if err != nil {
t.Fatal(err)
}
cacheRoot := t.TempDir()
updated := strings.Replace(string(content), "directory: ./notarius-cache/chunk-plans", fmt.Sprintf("directory: %q", filepath.Join(cacheRoot, "chunk-plans")), 1)
updated = strings.Replace(updated, "directory: ./notarius-cache/checkpoints", fmt.Sprintf("directory: %q", filepath.Join(cacheRoot, "checkpoints")), 1)
for relative, absolute := range map[string]string{
"./dnd-party.txt": repositoryPath("examples", "dnd-party.txt"),
"./dnd-glossary.txt": repositoryPath("examples", "dnd-glossary.txt"),
"./dnd-spell-catalog.json": repositoryPath("examples", "dnd-spell-catalog.json"),
} {
updated = strings.ReplaceAll(updated, relative, fmt.Sprintf("%q", absolute))
}
path := filepath.Join(t.TempDir(), "dnd-complete.config.yml")
if err := os.WriteFile(path, []byte(updated), 0o600); err != nil {
t.Fatal(err)
}
return path
}
type enemyEventLLMClient struct {
mu sync.Mutex
requests []contracts.StructuredCompletionRequest
}
func (client *enemyEventLLMClient) CompleteStructured(ctx context.Context, request contracts.StructuredCompletionRequest, output any) (contracts.StructuredCompletionResponse, error) {
if err := ctx.Err(); err != nil {
return contracts.StructuredCompletionResponse{}, err
}
combatScene := strings.Contains(string(request.Inputs["transcript"].Content), "Roll initiative")
var content []byte
switch request.PromptID {
case scenes.PromptID:
content = []byte(`{"scenes":[{"start_unit_id":1,"end_unit_id":6},{"start_unit_id":7,"end_unit_id":11}]}`)
case npcs.PromptID:
if combatScene {
content = []byte(`{"npcs":[{"name":"Kesh","source_refs":[{"start_unit_id":7,"end_unit_id":7}]}]}`)
} else {
content = []byte(`{"npcs":[]}`)
}
case npcnormalize.PromptID:
content = []byte(`{"duplicate_groups":[]}`)
case scenedescriptions.PromptID:
kind, title := "narrative", "Arrival"
if combatScene {
kind, title = "combat", "Raiders attack"
}
content = []byte(fmt.Sprintf(`{"kind":%q,"title":%q,"summary":"session scene"}`, kind, title))
case spells.PromptID:
content = []byte(`{"spell_casts":[]}`)
case itemevents.PromptID:
content = []byte(`{"events":[]}`)
case combat.PromptID:
content = []byte(`{"combat_turns":[{"actor":"Kesh","turn_kind":"turn","source_refs":[{"start_unit_id":8,"end_unit_id":8}]}]}`)
case npcinteractions.PromptID:
if combatScene {
content = []byte(`{"interactions":[{"name":"Kesh","kind":"combat_opponent","source_refs":[{"start_unit_id":7,"end_unit_id":7}]}]}`)
} else {
content = []byte(`{"interactions":[]}`)
}
case enemyevents.PromptID:
content = []byte(`{"events":[{"name":"Kesh","kind":"fled","source_refs":[{"start_unit_id":10,"end_unit_id":10}]}]}`)
default:
return contracts.StructuredCompletionResponse{}, fmt.Errorf("unexpected prompt %q", request.PromptID)
}
if err := json.Unmarshal(content, output); err != nil {
return contracts.StructuredCompletionResponse{}, fmt.Errorf("populate fake structured target: %w", err)
}
client.mu.Lock()
client.requests = append(client.requests, request)
client.mu.Unlock()
return contracts.StructuredCompletionResponse{Content: content, Provider: "test", Model: "deterministic", ProfileID: request.ProfileID}, nil
}
func (client *enemyEventLLMClient) requestsFor(promptID string) []contracts.StructuredCompletionRequest {
client.mu.Lock()
defer client.mu.Unlock()
var requests []contracts.StructuredCompletionRequest
for _, request := range client.requests {
if request.PromptID == promptID {
requests = append(requests, request)
}
}
return requests
}
func containsString(values []string, want string) bool {
for _, value := range values {
if value == want {
return true
}
}
return false
}
func evidenceHasLane(value evidencecontext.Document, laneID string) bool {
for _, context := range value.Contexts {
for _, reference := range context.EvidenceRefs {
if reference.LaneID == laneID {
return true
}
}
}
return false
}
func generatedReferenceBinding(bindings []pipeline.ReferenceBinding, slotName string) (pipeline.ReferenceBinding, bool) {
for _, binding := range bindings {
if binding.SlotName == slotName && binding.Artifact != nil {
return binding, true
}
}
return pipeline.ReferenceBinding{}, false
}