775 lines
34 KiB
Go
775 lines
34 KiB
Go
package cli
|
|
|
|
import (
|
|
"context"
|
|
"encoding/json"
|
|
"errors"
|
|
"fmt"
|
|
"io/fs"
|
|
"os"
|
|
"path/filepath"
|
|
"reflect"
|
|
"runtime"
|
|
"sort"
|
|
"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/chunkmap"
|
|
"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
|
|
"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"
|
|
combatcodec "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/codec/combatturns"
|
|
spellcodec "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/codec/spells"
|
|
combatextract "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/combatturns"
|
|
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/spells"
|
|
combatnormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/combatturns"
|
|
spellnormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/spells"
|
|
"gitea.maximumdirect.net/eric/notarius/internal/modules/generic/normalize/noop"
|
|
)
|
|
|
|
func TestProductionCatalogCoversMaintainedConfigurations(t *testing.T) {
|
|
components := productionTestComponents(t)
|
|
registries := components.registries
|
|
|
|
assertProductionContains(t, "inputs", registries.Inputs.RegisteredKeys(), []string{"seriatim"})
|
|
assertProductionContains(t, "chunkers", registries.Chunkers.RegisteredKeys(), []string{"dnd/scenes", "generic"})
|
|
assertProductionContains(t, "extractors", registries.Extractors.RegisteredKeys(), []string{"dnd/spells", "dnd/npcs", combatextract.Key})
|
|
assertProductionContains(t, "mergers", registries.Mergers.RegisteredKeys(), []string{"appendorder"})
|
|
assertProductionContains(t, "normalizers", registries.Normalizers.RegisteredKeys(), []string{"noop", spellnormalize.Key, "dnd/npcs", combatnormalize.Key})
|
|
assertProductionContains(t, "outputs", registries.Outputs.RegisteredKeys(), []string{"json"})
|
|
assertProductionContains(t, "validators", registries.Validators.RegisteredKeys(), []string{
|
|
"extract/dnd/spells/catalog",
|
|
"extract/dnd/spells/shape",
|
|
"extract/dnd/spells/source_refs",
|
|
"extract/dnd/spells/source_relatedness",
|
|
"extract/dnd/combat-turns/shape",
|
|
"extract/dnd/combat-turns/source_refs",
|
|
"extract/dnd/combat-turns/source_relatedness",
|
|
"normalize/dnd/combat-turns/invariants",
|
|
"generic/always_accept",
|
|
"generic/always_reject",
|
|
"generic/valid_json",
|
|
"generic/valid_json_schema",
|
|
})
|
|
assertProductionContains(t, "artifact codec kinds", registries.ArtifactCodecs.RegisteredKinds(), []contracts.ArtifactKind{dnd.SpellListKind, dnd.NPCListKind, dnd.CombatTurnListKind})
|
|
assertProductionContains(t, "merger variants", registries.Mergers.RegisteredArtifactKinds(pipeline.DefaultMergeModule), []contracts.ArtifactKind{dnd.SpellListKind, dnd.NPCListKind, dnd.CombatTurnListKind})
|
|
assertProductionContains(t, "normalizer variants", registries.Normalizers.RegisteredArtifactKinds(pipeline.DefaultNormalizeModule), []contracts.ArtifactKind{dnd.SpellListKind, dnd.NPCListKind, dnd.CombatTurnListKind})
|
|
assertProductionContains(t, "spell normalizer variants", registries.Normalizers.RegisteredArtifactKinds(spellnormalize.Key), []contracts.ArtifactKind{dnd.SpellListKind})
|
|
assertProductionContains(t, "combat normalizer variants", registries.Normalizers.RegisteredArtifactKinds(combatnormalize.Key), []contracts.ArtifactKind{dnd.CombatTurnListKind})
|
|
|
|
wantChain := []pipeline.ModuleBinding{
|
|
pipeline.Binding("generic/valid_json"),
|
|
pipeline.Binding("extract/dnd/spells/shape"),
|
|
pipeline.Binding("extract/dnd/spells/catalog"),
|
|
pipeline.Binding("extract/dnd/spells/source_refs"),
|
|
pipeline.Binding("generic/valid_json_schema"),
|
|
pipeline.Binding("extract/dnd/spells/source_relatedness"),
|
|
}
|
|
if got := registries.ValidatorChains.Validators(pipeline.StageExtract, spells.Key); !reflect.DeepEqual(got, wantChain) {
|
|
t.Fatalf("spell validator chain = %#v, want %#v", got, wantChain)
|
|
}
|
|
if got := registries.ValidatorChains.Validators(pipeline.StageNormalize, spellnormalize.Key); !reflect.DeepEqual(got, wantChain) {
|
|
t.Fatalf("spell normalize validator chain = %#v, want %#v", got, wantChain)
|
|
}
|
|
combatExtractChain := []pipeline.ModuleBinding{
|
|
pipeline.Binding("generic/valid_json"),
|
|
pipeline.Binding("extract/dnd/combat-turns/shape"),
|
|
pipeline.Binding("extract/dnd/combat-turns/source_refs"),
|
|
pipeline.Binding("generic/valid_json_schema"),
|
|
pipeline.Binding("extract/dnd/combat-turns/source_relatedness"),
|
|
}
|
|
combatNormalizeChain := []pipeline.ModuleBinding{
|
|
pipeline.Binding("generic/valid_json"),
|
|
pipeline.Binding("extract/dnd/combat-turns/shape"),
|
|
pipeline.Binding("normalize/dnd/combat-turns/invariants"),
|
|
pipeline.Binding("extract/dnd/combat-turns/source_refs"),
|
|
pipeline.Binding("generic/valid_json_schema"),
|
|
pipeline.Binding("extract/dnd/combat-turns/source_relatedness"),
|
|
}
|
|
if got := registries.ValidatorChains.Validators(pipeline.StageExtract, combatextract.Key); !reflect.DeepEqual(got, combatExtractChain) {
|
|
t.Fatalf("combat extract validator chain = %#v, want %#v", got, combatExtractChain)
|
|
}
|
|
if got := registries.ValidatorChains.Validators(pipeline.StageNormalize, combatnormalize.Key); !reflect.DeepEqual(got, combatNormalizeChain) {
|
|
t.Fatalf("combat normalize validator chain = %#v, want %#v", got, combatNormalizeChain)
|
|
}
|
|
|
|
assetNames := productionAssetNames(t, components.assets.PromptFS)
|
|
requiredAssets := []string{
|
|
"dnd.scenes/dnd.scenes.yaml",
|
|
"dnd.scenes/instructions.md",
|
|
"dnd.scenes/sharedassets/common-dnd-references.md",
|
|
"dnd.scenes/sharedassets/common-dnd-system.md",
|
|
"dnd.scenes/sharedassets/common-dnd-transcript.md",
|
|
"dnd.scenes/task.md",
|
|
"dnd.spells/dnd.spells.yaml",
|
|
"dnd.spells/catalog.md",
|
|
"dnd.spells/instructions.md",
|
|
"dnd.spells/sharedassets/common-dnd-references.md",
|
|
"dnd.spells/sharedassets/common-dnd-system.md",
|
|
"dnd.spells/sharedassets/common-dnd-transcript.md",
|
|
"dnd.spells/task.md",
|
|
"dnd.combat_turns/dnd.combat_turns.yaml",
|
|
"dnd.combat_turns/instructions.md",
|
|
"dnd.combat_turns/sharedassets/common-dnd-references.md",
|
|
"dnd.combat_turns/sharedassets/common-dnd-system.md",
|
|
"dnd.combat_turns/sharedassets/common-dnd-transcript.md",
|
|
"dnd.combat_turns/task.md",
|
|
}
|
|
assertProductionContains(t, "production prompt assets", assetNames, requiredAssets)
|
|
|
|
catalog := catalogFromRegistries(registries)
|
|
converted := registriesFromCatalog(catalog)
|
|
if converted.ArtifactCodecs != registries.ArtifactCodecs || converted.ValidatorChains != registries.ValidatorChains {
|
|
t.Fatal("catalog/registry conversion did not preserve codec and validator-chain registries")
|
|
}
|
|
codecSpec, ok := catalog.ArtifactCodecs.Spec(dnd.SpellListKind)
|
|
if !ok || codecSpec.Kind != dnd.SpellListKind || codecSpec.Schema.ID != spellcodec.SchemaID {
|
|
t.Fatalf("catalog codec spec = %#v, ok=%t, want typed D&D spell codec", codecSpec, ok)
|
|
}
|
|
combatCodecSpec, ok := catalog.ArtifactCodecs.Spec(dnd.CombatTurnListKind)
|
|
if !ok || combatCodecSpec.Kind != dnd.CombatTurnListKind || combatCodecSpec.Schema.ID != combatcodec.SchemaID {
|
|
t.Fatalf("combat codec spec = %#v, ok=%t, want typed D&D combat codec", combatCodecSpec, ok)
|
|
}
|
|
if got := catalog.ValidatorChains.Validators(pipeline.StageExtract, spells.Key); !reflect.DeepEqual(got, wantChain) {
|
|
t.Fatalf("catalog validator chain = %#v, want %#v", got, wantChain)
|
|
}
|
|
if got := catalog.ValidatorChains.Validators(pipeline.StageNormalize, spellnormalize.Key); !reflect.DeepEqual(got, wantChain) {
|
|
t.Fatalf("catalog spell normalize validator chain = %#v, want %#v", got, wantChain)
|
|
}
|
|
|
|
}
|
|
|
|
func TestDefaultCLICompositionValidatesRepresentativeConfiguration(t *testing.T) {
|
|
var stdout, stderr strings.Builder
|
|
code := RunWithOptions([]string{
|
|
"config", "validate", "--config", repositoryPath("examples", "dnd-spells.config.yml"), "--pipeline", "dnd-session",
|
|
}, &stdout, &stderr, Options{})
|
|
if code != 0 || stderr.Len() != 0 {
|
|
t.Fatalf("validate representative config with default composition: code=%d stdout=%q stderr=%q", code, stdout.String(), stderr.String())
|
|
}
|
|
}
|
|
|
|
func TestProductionPromptAssetsPrepareWithoutProviderCredentials(t *testing.T) {
|
|
components := productionTestComponents(t)
|
|
cfg := config.Default()
|
|
cfg.Pipelines["dnd-scenes"] = pipeline.PipelineProfile{
|
|
ID: "dnd-scenes",
|
|
Input: pipeline.Binding("seriatim"),
|
|
Chunk: pipeline.Binding("dnd/scenes"),
|
|
Artifacts: map[string]pipeline.ArtifactLaneProfile{
|
|
"spells": {Extract: pipeline.Binding("dnd/spells")},
|
|
},
|
|
}
|
|
effective, err := cfg.Resolve(config.ResolveInput{PipelineID: "dnd-scenes", Catalog: catalogFromRegistries(components.registries)})
|
|
if err != nil {
|
|
t.Fatalf("resolve production scene pipeline: %v", err)
|
|
}
|
|
if _, err := pipeline.Prepare(effective.ResolvedPipeline, components.registries, pipeline.ModuleDependencies{LLM: &productionFakeLLMClient{}}); err != nil {
|
|
t.Fatalf("prepare production scene and spell modules: %v", err)
|
|
}
|
|
}
|
|
|
|
func TestProductionSpellValidatorsPrepareFromMaterializedCatalog(t *testing.T) {
|
|
components := productionTestComponents(t)
|
|
configPath := repositoryPath("examples", "dnd-spells-production.config.yml")
|
|
effective, err := loadMaintainedExample(t, configPath).Resolve(resolveInputForMaintainedExample(components, "dnd-session"))
|
|
if err != nil {
|
|
t.Fatalf("resolve production spell configuration: %v", err)
|
|
}
|
|
materialized, _, err := pipeline.MaterializeReferences(effective.ResolvedPipeline, catalogFromRegistries(components.registries), pipeline.ReferenceMaterializationOptions{
|
|
ConfigPath: configPath,
|
|
WorkingDir: filepath.Dir(configPath),
|
|
})
|
|
if err != nil {
|
|
t.Fatalf("materialize production spell references: %v", err)
|
|
}
|
|
extractItems := materialized.Steps[0].ArtifactLanes[0].ExtractReferences.ReferenceSet.Slots["spell_catalog"].Items
|
|
normalizeItems := materialized.Steps[0].ArtifactLanes[0].NormalizeReferences.ReferenceSet.Slots["spell_catalog"].Items
|
|
if len(extractItems) != 1 || extractItems[0].MediaType != "application/json" || len(extractItems[0].Content) == 0 {
|
|
t.Fatalf("materialized extract spell catalog items = %#v, want one JSON item", extractItems)
|
|
}
|
|
if len(normalizeItems) != 1 || normalizeItems[0].MediaType != "application/json" || !reflect.DeepEqual(normalizeItems[0].Content, extractItems[0].Content) {
|
|
t.Fatalf("materialized normalize spell catalog items = %#v, want an independent binding of the extract catalog", normalizeItems)
|
|
}
|
|
if _, err := pipeline.Prepare(materialized, components.registries, pipeline.ModuleDependencies{LLM: &productionFakeLLMClient{}}); err != nil {
|
|
t.Fatalf("prepare production spell pipeline from materialized catalog: %v", err)
|
|
}
|
|
}
|
|
|
|
func TestProductionSpellNormalizerRejectsInvalidCatalogReferencesBeforeExecution(t *testing.T) {
|
|
components := productionTestComponents(t)
|
|
configPath := repositoryPath("examples", "dnd-spells-production.config.yml")
|
|
resolve := func(t *testing.T) pipeline.ResolvedPipeline {
|
|
t.Helper()
|
|
effective, err := loadMaintainedExample(t, configPath).Resolve(resolveInputForMaintainedExample(components, "dnd-session"))
|
|
if err != nil {
|
|
t.Fatalf("resolve production spell configuration: %v", err)
|
|
}
|
|
return effective.ResolvedPipeline
|
|
}
|
|
materialize := func(resolved pipeline.ResolvedPipeline) (pipeline.ResolvedPipeline, error) {
|
|
materialized, _, err := pipeline.MaterializeReferences(resolved, catalogFromRegistries(components.registries), pipeline.ReferenceMaterializationOptions{
|
|
ConfigPath: configPath,
|
|
WorkingDir: filepath.Dir(configPath),
|
|
})
|
|
return materialized, err
|
|
}
|
|
|
|
t.Run("malformed catalog fails preparation", func(t *testing.T) {
|
|
catalogPath := filepath.Join(t.TempDir(), "malformed.json")
|
|
if err := os.WriteFile(catalogPath, []byte(`{"schema_version":`), 0o600); err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
resolved := resolve(t)
|
|
setNormalizeSpellCatalogSource(t, &resolved, catalogPath)
|
|
materialized, err := materialize(resolved)
|
|
if err != nil {
|
|
t.Fatalf("MaterializeReferences() error = %v, want malformed JSON to reach preparation", err)
|
|
}
|
|
_, err = pipeline.Prepare(materialized, components.registries, pipeline.ModuleDependencies{LLM: &productionFakeLLMClient{}})
|
|
for _, fragment := range []string{`pipeline "dnd-session"`, `lane "spells"`, "normalize", `module "dnd/spells"`, "decode spell catalog overlay"} {
|
|
if err == nil || !strings.Contains(err.Error(), fragment) {
|
|
t.Fatalf("Prepare() error = %v, want context fragment %q", err, fragment)
|
|
}
|
|
}
|
|
})
|
|
|
|
t.Run("multiple catalog items fail preparation", func(t *testing.T) {
|
|
materialized, err := materialize(resolve(t))
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
slot := materialized.Steps[0].ArtifactLanes[0].NormalizeReferences.ReferenceSet.Slots["spell_catalog"]
|
|
slot.Items = append(slot.Items, slot.Items[0])
|
|
materialized.Steps[0].ArtifactLanes[0].NormalizeReferences.ReferenceSet.Slots["spell_catalog"] = slot
|
|
_, err = pipeline.Prepare(materialized, components.registries, pipeline.ModuleDependencies{LLM: &productionFakeLLMClient{}})
|
|
for _, fragment := range []string{"normalize", `module "dnd/spells"`, "zero or one item"} {
|
|
if err == nil || !strings.Contains(err.Error(), fragment) {
|
|
t.Fatalf("Prepare() error = %v, want context fragment %q", err, fragment)
|
|
}
|
|
}
|
|
})
|
|
|
|
t.Run("oversized catalog fails materialization", func(t *testing.T) {
|
|
catalogPath := filepath.Join(t.TempDir(), "oversized.json")
|
|
if err := os.WriteFile(catalogPath, []byte(strings.Repeat("x", 1048577)), 0o600); err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
checkpointRoot := filepath.Join(t.TempDir(), "checkpoints")
|
|
content := string(readRepositoryFile(t, "examples", "dnd-spells-production.config.yml"))
|
|
content = replaceRequiredOnce(t, content, "./dnd-spells-roster.txt", repositoryPath("examples", "dnd-spells-roster.txt"))
|
|
content = replaceRequiredOnce(t, content, "./dnd-spells-glossary.txt", repositoryPath("examples", "dnd-spells-glossary.txt"))
|
|
content = strings.Replace(content, "./dnd-spells-catalog.json", repositoryPath("examples", "dnd-spells-catalog.json"), 1)
|
|
content = replaceRequiredOnce(t, content, "./dnd-spells-catalog.json", catalogPath)
|
|
content = replaceRequiredOnce(t, content, " enabled: false\n directory: /var/cache/notarius/checkpoints", " enabled: true\n directory: "+checkpointRoot)
|
|
configFile := filepath.Join(t.TempDir(), "config.yml")
|
|
if err := os.WriteFile(configFile, []byte(content), 0o600); err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
|
|
llmConstructed := false
|
|
chunkStoreConstructed := false
|
|
options := Options{
|
|
Catalog: catalogFromRegistries(components.registries),
|
|
Registries: components.registries,
|
|
LLMClientFactory: func(context.Context, config.Config, string) (contracts.StructuredLLMClient, []artifacts.LLMProfileManifest, error) {
|
|
llmConstructed = true
|
|
return nil, nil, errors.New("LLM client must not be constructed")
|
|
},
|
|
ChunkPlanStoreFactory: func(string) (pipeline.ChunkPlanStore, error) {
|
|
chunkStoreConstructed = true
|
|
return nil, errors.New("chunk-plan store must not be constructed")
|
|
},
|
|
}
|
|
var stdout, stderr strings.Builder
|
|
code := RunWithOptions([]string{
|
|
"run", "dnd-session", "--config", configFile,
|
|
"--input", repositoryPath("examples", "seriatim-minimal-transcript.json"),
|
|
}, &stdout, &stderr, options)
|
|
errText := stderr.String()
|
|
for _, fragment := range []string{"normalize", `lane "spells"`, `reference slot "spell_catalog"`, "1048577 bytes", "limit 1048576"} {
|
|
if code == 0 || !strings.Contains(errText, fragment) {
|
|
t.Fatalf("RunWithOptions() code = %d stderr = %q, want context fragment %q", code, errText, fragment)
|
|
}
|
|
}
|
|
if llmConstructed || chunkStoreConstructed {
|
|
t.Fatalf("runtime construction = LLM %t, chunk store %t; want materialization failure first", llmConstructed, chunkStoreConstructed)
|
|
}
|
|
if _, err := os.Stat(checkpointRoot); !errors.Is(err, fs.ErrNotExist) {
|
|
t.Fatalf("checkpoint root stat error = %v, want no checkpoint allocation", err)
|
|
}
|
|
})
|
|
}
|
|
|
|
func setNormalizeSpellCatalogSource(t *testing.T, resolved *pipeline.ResolvedPipeline, sourcePath string) {
|
|
t.Helper()
|
|
if resolved == nil || len(resolved.Steps[0].ArtifactLanes) != 1 {
|
|
t.Fatalf("resolved pipeline = %#v, want one artifact lane", resolved)
|
|
}
|
|
bindings := resolved.Steps[0].ArtifactLanes[0].NormalizeReferences.Bindings
|
|
matches := 0
|
|
for index := range bindings {
|
|
if bindings[index].SlotName == "spell_catalog" {
|
|
bindings[index].Source = sourcePath
|
|
matches++
|
|
}
|
|
}
|
|
if matches != 1 {
|
|
t.Fatalf("normalize reference bindings = %#v, want exactly one spell_catalog binding", bindings)
|
|
}
|
|
resolved.Steps[0].ArtifactLanes[0].NormalizeReferences.Bindings = bindings
|
|
}
|
|
|
|
func TestProductionLLMClientFactoriesBuildOfflineRuntime(t *testing.T) {
|
|
components := productionTestComponents(t)
|
|
factories := []struct {
|
|
name string
|
|
factory LLMClientFactory
|
|
}{
|
|
{name: "default production assets", factory: productionLLMClientFactory},
|
|
{name: "provided production assets", factory: productionLLMClientFactoryWithAssets(components.assets)},
|
|
}
|
|
for _, tt := range factories {
|
|
t.Run(tt.name, func(t *testing.T) {
|
|
client, manifests, err := tt.factory(context.Background(), config.Default(), "test-profile")
|
|
if err != nil {
|
|
t.Fatalf("build production LLM runtime: %v", err)
|
|
}
|
|
if client == nil {
|
|
t.Fatal("production LLM runtime returned a nil client")
|
|
}
|
|
if len(manifests) != 0 {
|
|
t.Fatalf("eager profile manifests = %#v, want none", manifests)
|
|
}
|
|
if _, ok := client.(contracts.LLMProfileManifestProvider); !ok {
|
|
t.Fatalf("production LLM client %T does not provide profile manifests", client)
|
|
}
|
|
})
|
|
}
|
|
}
|
|
|
|
func TestProductionLLMClientFactoriesRejectInvalidConstruction(t *testing.T) {
|
|
t.Run("canceled context", func(t *testing.T) {
|
|
ctx, cancel := context.WithCancel(context.Background())
|
|
cancel()
|
|
client, manifests, err := productionLLMClientFactory(ctx, config.Default(), "test-profile")
|
|
if !errors.Is(err, context.Canceled) || client != nil || len(manifests) != 0 {
|
|
t.Fatalf("client=%T manifests=%#v error=%v, want canceled construction", client, manifests, err)
|
|
}
|
|
})
|
|
|
|
t.Run("nil assets", func(t *testing.T) {
|
|
client, manifests, err := productionLLMClientFactoryWithAssets(nil)(context.Background(), config.Default(), "test-profile")
|
|
if err == nil || !strings.Contains(err.Error(), "asset registry must not be nil") || client != nil || len(manifests) != 0 {
|
|
t.Fatalf("client=%T manifests=%#v error=%v, want nil-assets failure", client, manifests, err)
|
|
}
|
|
})
|
|
|
|
t.Run("invalid scheduler concurrency", func(t *testing.T) {
|
|
components := productionTestComponents(t)
|
|
cfg := config.Default()
|
|
cfg.Concurrency.TotalLLM = 0
|
|
client, manifests, err := productionLLMClientFactoryWithAssets(components.assets)(context.Background(), cfg, "test-profile")
|
|
if err == nil || !strings.Contains(err.Error(), "create LLM scheduler") || !strings.Contains(err.Error(), "greater than zero") || client != nil || len(manifests) != 0 {
|
|
t.Fatalf("client=%T manifests=%#v error=%v, want scheduler-construction failure", client, manifests, err)
|
|
}
|
|
})
|
|
}
|
|
|
|
func TestProductionConfigValidationCoversModuleAndVariantFailures(t *testing.T) {
|
|
base := string(readRepositoryFile(t, "examples", "dnd-spells.config.yml"))
|
|
validPath := writeProductionContractConfig(t, base)
|
|
options := productionCLIOptions(t)
|
|
var stdout, stderr strings.Builder
|
|
if code := RunWithOptions([]string{"config", "validate", "--config", validPath, "--pipeline", "dnd-session"}, &stdout, &stderr, options); code != 0 {
|
|
t.Fatalf("valid production config: code=%d stdout=%q stderr=%q", code, stdout.String(), stderr.String())
|
|
}
|
|
tests := []struct {
|
|
name string
|
|
content string
|
|
options Options
|
|
fragments []string
|
|
}{
|
|
{
|
|
name: "unknown module",
|
|
content: replaceRequiredOnce(t, base, " input: seriatim\n", " input: missing/input\n"),
|
|
options: productionCLIOptions(t),
|
|
fragments: []string{"pipeline \"dnd-session\"", "input", "missing/input"},
|
|
},
|
|
{
|
|
name: "unknown validator",
|
|
content: replaceRequiredOnce(t, base, " extract: dnd/spells\n", " extract:\n module: dnd/spells\n validators:\n - module: missing/validator\n"),
|
|
options: productionCLIOptions(t),
|
|
fragments: []string{"validator", "missing/validator"},
|
|
},
|
|
{
|
|
name: "invalid artifact variant",
|
|
content: base,
|
|
options: productionCLIOptionsWithoutSpellNormalizer(t),
|
|
fragments: []string{"normalizer", spellnormalize.Key, string(dnd.SpellListKind), "variant"},
|
|
},
|
|
{
|
|
name: "deterministic validator with profile",
|
|
content: replaceRequiredOnce(t, base, " extract: dnd/spells\n", " extract:\n module: dnd/spells\n validators:\n - module: generic/valid_json\n llm_profile: forbidden-profile\n"),
|
|
options: productionCLIOptions(t),
|
|
fragments: []string{"deterministic validator", "llm_profile"},
|
|
},
|
|
}
|
|
for _, tt := range tests {
|
|
t.Run(tt.name, func(t *testing.T) {
|
|
path := writeProductionContractConfig(t, tt.content)
|
|
var stdout, stderr strings.Builder
|
|
code := RunWithOptions([]string{"config", "validate", "--config", path, "--pipeline", "dnd-session"}, &stdout, &stderr, tt.options)
|
|
if code != 1 {
|
|
t.Fatalf("code=%d stdout=%q stderr=%q", code, stdout.String(), stderr.String())
|
|
}
|
|
for _, fragment := range tt.fragments {
|
|
if !strings.Contains(stderr.String(), fragment) {
|
|
t.Fatalf("stderr=%q, want %q", stderr.String(), fragment)
|
|
}
|
|
}
|
|
})
|
|
}
|
|
}
|
|
|
|
func TestProductionNormalizeValidatorOverrideRemainsAuthoritative(t *testing.T) {
|
|
base := string(readRepositoryFile(t, "examples", "dnd-spells.config.yml"))
|
|
content := replaceRequiredOnce(t, base, " normalize: dnd/spells\n", " normalize:\n module: dnd/spells\n validators:\n - module: generic/always_accept\n - module: generic/valid_json\n")
|
|
path := writeProductionContractConfig(t, content)
|
|
components := productionTestComponents(t)
|
|
effective, err := loadMaintainedExample(t, path).Resolve(resolveInputForMaintainedExample(components, "dnd-session"))
|
|
if err != nil {
|
|
t.Fatalf("resolve normalize override: %v", err)
|
|
}
|
|
for _, chain := range effective.ResolvedPipeline.ValidatorChains {
|
|
if chain.Stage != pipeline.StageNormalize || chain.ModuleKey != spellnormalize.Key {
|
|
continue
|
|
}
|
|
if len(chain.Validators) != 2 || chain.Validators[0].Binding.Module != "generic/always_accept" || chain.Validators[1].Binding.Module != "generic/valid_json" {
|
|
t.Fatalf("normalize validator chain = %#v, want explicit validator order", chain)
|
|
}
|
|
return
|
|
}
|
|
t.Fatalf("resolved validator chains = %#v, want normalize chain for %q", effective.ResolvedPipeline.ValidatorChains, spellnormalize.Key)
|
|
}
|
|
|
|
func TestProductionSceneRunRecordsAnnotationFreeChunkPlanAndProvenance(t *testing.T) {
|
|
outputRoot := filepath.Join(t.TempDir(), "output")
|
|
configPath := writeProductionContractConfig(t, productionRunConfig(outputRoot, "dnd/scenes"))
|
|
fake := &productionFakeLLMClient{}
|
|
options := productionRunOptions(t, fake)
|
|
var stdout, stderr strings.Builder
|
|
code := RunWithOptions([]string{
|
|
"run", "dnd-session", "--config", configPath,
|
|
"--input", repositoryPath("examples", "seriatim-minimal-transcript.json"),
|
|
"--chunk_cache", "bypass", "--session-id", "offline-session",
|
|
}, &stdout, &stderr, options)
|
|
if code != 0 {
|
|
t.Fatalf("code=%d stdout=%q stderr=%q", code, stdout.String(), stderr.String())
|
|
}
|
|
manifest := readProductionJSON[artifacts.RunManifest](t, filepath.Join(outputRoot, productionRunID, "manifest.json"))
|
|
if manifest.Chunker != scenes.Key || manifest.ChunkPlan == nil || manifest.ChunkPlan.Action != "bypassed" || manifest.ChunkPlan.ProducerModule != scenes.Key {
|
|
t.Fatalf("chunk manifest = %#v, want dnd scene producer", manifest.ChunkPlan)
|
|
}
|
|
if got := manifest.ModuleMetadata["chunker"]["prompt_id"]; got != scenes.PromptID {
|
|
t.Fatalf("chunker prompt metadata = %#v, want %q", got, scenes.PromptID)
|
|
}
|
|
if got := manifest.ChunkPlan.ProducerMetadata["response_schema_id"]; got != scenes.ResponseSchemaID {
|
|
t.Fatalf("chunk producer schema metadata = %#v, want %q", got, scenes.ResponseSchemaID)
|
|
}
|
|
index := readProductionJSON[productionChunkMapIndex](t, filepath.Join(outputRoot, productionRunID, "index.json"))
|
|
if index.ChunkMap == nil || index.ChunkMap.ArtifactKind != chunkmap.ArtifactKind || index.ChunkMap.File != "chunk-map.json" || index.ChunkMap.MediaType != chunkmap.MediaType || index.ChunkMap.SchemaID != chunkmap.SchemaID || index.ChunkMap.SchemaName != chunkmap.SchemaName || index.ChunkMap.SchemaVersion != chunkmap.SchemaVersion {
|
|
t.Fatalf("chunk map index = %#v, want fixed chunk map descriptor", index.ChunkMap)
|
|
}
|
|
for _, output := range index.OutputFiles {
|
|
if output.File == index.ChunkMap.File {
|
|
t.Fatalf("lane output files = %#v, want no chunk map", index.OutputFiles)
|
|
}
|
|
}
|
|
content, err := os.ReadFile(filepath.Join(outputRoot, productionRunID, index.ChunkMap.File))
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
chunkMap, err := chunkmap.New().Decode(content)
|
|
if err != nil {
|
|
t.Fatalf("Decode(chunk map) error = %v", err)
|
|
}
|
|
if chunkMap.SourceID != "session-alpha" || chunkMap.SourceDigest != manifest.ChunkPlan.SourceDigest || chunkMap.PlanDigest != manifest.ChunkPlan.PlanDigest || chunkMap.RequestedChunker != scenes.Key || chunkMap.Producer.InputModule != "seriatim" || chunkMap.Producer.ChunkModule != scenes.Key || chunkMap.Producer.LLMProfile != manifest.ChunkPlan.ProducerLLMProfile {
|
|
t.Fatalf("chunk map identity and producer = %#v, want accepted scene plan provenance", chunkMap)
|
|
}
|
|
if len(chunkMap.Chunks) != 1 || chunkMap.Chunks[0].ID != "chunk-000001" || chunkMap.Chunks[0].Index != 0 || chunkMap.Chunks[0].SourceRef.SourceID != "session-alpha" || chunkMap.Chunks[0].SourceRef.StartUnitID != 1 || chunkMap.Chunks[0].SourceRef.EndUnitID != 2 || chunkMap.Chunks[0].UnitCount != 2 {
|
|
t.Fatalf("chunk map chunks = %#v, want one stable accepted scene range", chunkMap.Chunks)
|
|
}
|
|
if len(chunkMap.PlanAnnotations) != 0 {
|
|
t.Fatalf("chunk map plan annotations = %#v, want none", chunkMap.PlanAnnotations)
|
|
}
|
|
if len(chunkMap.Chunks[0].Annotations) != 0 {
|
|
t.Fatalf("chunk map range annotations = %#v, want none", chunkMap.Chunks[0].Annotations)
|
|
}
|
|
warnings := readProductionJSON[struct {
|
|
Warnings []contracts.Warning `json:"warnings"`
|
|
}](t, filepath.Join(outputRoot, productionRunID, "warnings.json"))
|
|
if len(warnings.Warnings) != 0 {
|
|
t.Fatalf("warnings = %#v, want none", warnings.Warnings)
|
|
}
|
|
if len(fake.requestsFor(scenes.PromptID)) != 1 || len(fake.requestsFor(spells.PromptID)) != 1 {
|
|
t.Fatalf("fake prompt requests = %#v, want one scene and one spell request", fake.requestPrompts())
|
|
}
|
|
}
|
|
|
|
type maintainedExample struct {
|
|
name string
|
|
path string
|
|
pipelineIDs []string
|
|
}
|
|
|
|
func maintainedExampleFiles(t *testing.T) []maintainedExample {
|
|
t.Helper()
|
|
return []maintainedExample{
|
|
{name: "minimal", path: repositoryPath("examples", "dnd-spells.config.yml"), pipelineIDs: []string{"dnd-session"}},
|
|
{name: "production", path: repositoryPath("examples", "dnd-spells-production.config.yml"), pipelineIDs: []string{"dnd-session"}},
|
|
{name: "npcs", path: repositoryPath("examples", "dnd-npcs.config.yml"), pipelineIDs: []string{"dnd-session"}},
|
|
{name: "combat", path: repositoryPath("examples", "dnd-combat-turns.config.yml"), pipelineIDs: []string{"dnd-combat"}},
|
|
{name: "npc-grounded", path: repositoryPath("examples", "dnd-npc-grounded.config.yml"), pipelineIDs: []string{"dnd-npc-grounded"}},
|
|
{name: "npc-interactions", path: repositoryPath("examples", "dnd-npc-interactions.config.yml"), pipelineIDs: []string{"dnd-npc-interactions"}},
|
|
{name: "scene-descriptions", path: repositoryPath("examples", "dnd-scene-descriptions.config.yml"), pipelineIDs: []string{"dnd-scene-descriptions"}},
|
|
{name: "scene-chunk-map", path: repositoryPath("examples", "dnd-scene-chunk-map.config.yml"), pipelineIDs: []string{"dnd-scene-chunk-map"}},
|
|
}
|
|
}
|
|
|
|
func loadMaintainedExample(t *testing.T, path string) config.Config {
|
|
t.Helper()
|
|
fileConfig, err := config.LoadFileConfig(path)
|
|
if err != nil {
|
|
t.Fatalf("load maintained config %q: %v", path, err)
|
|
}
|
|
cfg := config.Default()
|
|
if err := cfg.ApplyFileConfig(fileConfig); err != nil {
|
|
t.Fatalf("apply maintained config %q: %v", path, err)
|
|
}
|
|
if err := cfg.Validate(); err != nil {
|
|
t.Fatalf("validate maintained config %q: %v", path, err)
|
|
}
|
|
return cfg
|
|
}
|
|
|
|
func productionTestComponents(t *testing.T) productionComponents {
|
|
t.Helper()
|
|
components, err := newProductionComponents()
|
|
if err != nil {
|
|
t.Fatalf("new production components: %v", err)
|
|
}
|
|
return components
|
|
}
|
|
|
|
func productionCLIOptions(t *testing.T) Options {
|
|
t.Helper()
|
|
components := productionTestComponents(t)
|
|
return productionOptionsFromComponents(components)
|
|
}
|
|
|
|
func productionOptionsFromComponents(components productionComponents) Options {
|
|
return Options{
|
|
Catalog: catalogFromRegistries(components.registries),
|
|
Registries: components.registries,
|
|
LookupEnv: emptyLookup,
|
|
}
|
|
}
|
|
|
|
func productionCLIOptionsWithoutSpellNormalizer(t *testing.T) Options {
|
|
t.Helper()
|
|
components := productionTestComponents(t)
|
|
registries := components.registries
|
|
registries.Normalizers = pipeline.NewNormalizerRegistry()
|
|
if err := noop.RegisterTyped[dnd.SpellList](registries.Normalizers, contracts.ArtifactKind("test/other")); err != nil {
|
|
t.Fatalf("register mismatched normalizer: %v", err)
|
|
}
|
|
return productionOptionsFromComponents(productionComponents{registries: registries, assets: components.assets})
|
|
}
|
|
|
|
const productionRunID = "run-1700000000000000000-0123456789abcdef0123456789abcdef"
|
|
|
|
func productionRunOptions(t *testing.T, fake *productionFakeLLMClient) Options {
|
|
t.Helper()
|
|
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) (contracts.StructuredLLMClient, []artifacts.LLMProfileManifest, error) {
|
|
return fake, nil, nil
|
|
}
|
|
return options
|
|
}
|
|
|
|
func productionRunConfig(outputRoot, chunkModule string) string {
|
|
return fmt.Sprintf(`version: 3
|
|
output:
|
|
directory: %q
|
|
cache:
|
|
chunk_plans:
|
|
mode: bypass
|
|
checkpoints: {}
|
|
debug:
|
|
directory: %q
|
|
pipelines:
|
|
dnd-session:
|
|
input: seriatim
|
|
chunk: %s
|
|
output:
|
|
module: json
|
|
options:
|
|
include_chunk_map: true
|
|
artifacts:
|
|
spells:
|
|
extract: dnd/spells
|
|
`, outputRoot, filepath.Join(filepath.Dir(outputRoot), "debug"), chunkModule)
|
|
}
|
|
|
|
type productionChunkMapIndex struct {
|
|
OutputFiles []struct {
|
|
File string `json:"file"`
|
|
} `json:"output_files"`
|
|
ChunkMap *struct {
|
|
ArtifactKind contracts.ArtifactKind `json:"artifact_kind"`
|
|
File string `json:"file"`
|
|
MediaType string `json:"media_type"`
|
|
SchemaID string `json:"schema_id"`
|
|
SchemaName string `json:"schema_name"`
|
|
SchemaVersion string `json:"schema_version"`
|
|
} `json:"chunk_map"`
|
|
}
|
|
|
|
func writeProductionContractConfig(t *testing.T, content string) string {
|
|
t.Helper()
|
|
path := filepath.Join(t.TempDir(), "config.yml")
|
|
if err := os.WriteFile(path, []byte(content), 0o600); err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
return path
|
|
}
|
|
|
|
func productionAssetNames(t *testing.T, getFS func() (fs.FS, error)) []string {
|
|
t.Helper()
|
|
fileSystem, err := getFS()
|
|
if err != nil {
|
|
t.Fatalf("load production prompt assets: %v", err)
|
|
}
|
|
var names []string
|
|
if err := fs.WalkDir(fileSystem, ".", func(path string, entry fs.DirEntry, err error) error {
|
|
if err != nil {
|
|
return err
|
|
}
|
|
if !entry.IsDir() {
|
|
names = append(names, path)
|
|
}
|
|
return nil
|
|
}); err != nil {
|
|
t.Fatalf("walk production prompt assets: %v", err)
|
|
}
|
|
sort.Strings(names)
|
|
return names
|
|
}
|
|
|
|
func assertProductionContains[T comparable](t *testing.T, name string, got, required []T) {
|
|
t.Helper()
|
|
available := make(map[T]struct{}, len(got))
|
|
for _, entry := range got {
|
|
available[entry] = struct{}{}
|
|
}
|
|
var missing []T
|
|
for _, entry := range required {
|
|
if _, ok := available[entry]; !ok {
|
|
missing = append(missing, entry)
|
|
}
|
|
}
|
|
if len(missing) > 0 {
|
|
t.Fatalf("%s missing required entries %#v; registered entries are %#v", name, missing, got)
|
|
}
|
|
}
|
|
|
|
func readProductionJSON[T any](t *testing.T, path string) T {
|
|
t.Helper()
|
|
data, err := os.ReadFile(path)
|
|
if err != nil {
|
|
t.Fatalf("read %s: %v", path, err)
|
|
}
|
|
var value T
|
|
if err := json.Unmarshal(data, &value); err != nil {
|
|
t.Fatalf("decode %s: %v", path, err)
|
|
}
|
|
return value
|
|
}
|
|
|
|
type productionFakeLLMClient struct {
|
|
mu sync.Mutex
|
|
requests []contracts.StructuredCompletionRequest
|
|
spellResponse string
|
|
}
|
|
|
|
func (client *productionFakeLLMClient) CompleteStructured(ctx context.Context, req contracts.StructuredCompletionRequest, out any) (contracts.StructuredCompletionResponse, error) {
|
|
if err := ctx.Err(); err != nil {
|
|
return contracts.StructuredCompletionResponse{}, err
|
|
}
|
|
var content []byte
|
|
switch req.PromptID {
|
|
case scenes.PromptID:
|
|
content = []byte(`{"scenes":[{"start_unit_id":1,"end_unit_id":2}]}`)
|
|
case spells.PromptID:
|
|
if client.spellResponse != "" {
|
|
content = []byte(client.spellResponse)
|
|
} else {
|
|
content = []byte(`{"spell_casts":[{"caster":"Aria","spell":"Cure Wounds","source_refs":[{"start_unit_id":1,"end_unit_id":1}]}]}`)
|
|
}
|
|
default:
|
|
return contracts.StructuredCompletionResponse{}, fmt.Errorf("unexpected prompt %q", req.PromptID)
|
|
}
|
|
if err := json.Unmarshal(content, out); err != nil {
|
|
return contracts.StructuredCompletionResponse{}, fmt.Errorf("populate fake structured target: %w", err)
|
|
}
|
|
client.mu.Lock()
|
|
client.requests = append(client.requests, req)
|
|
client.mu.Unlock()
|
|
return contracts.StructuredCompletionResponse{Content: content, Provider: "test", Model: "deterministic", ProfileID: req.ProfileID}, nil
|
|
}
|
|
|
|
func (client *productionFakeLLMClient) requestsFor(promptID string) []contracts.StructuredCompletionRequest {
|
|
client.mu.Lock()
|
|
defer client.mu.Unlock()
|
|
var requests []contracts.StructuredCompletionRequest
|
|
for _, req := range client.requests {
|
|
if req.PromptID == promptID {
|
|
requests = append(requests, req)
|
|
}
|
|
}
|
|
return requests
|
|
}
|
|
|
|
func (client *productionFakeLLMClient) requestPrompts() []string {
|
|
client.mu.Lock()
|
|
defer client.mu.Unlock()
|
|
prompts := make([]string, 0, len(client.requests))
|
|
for _, req := range client.requests {
|
|
prompts = append(prompts, req.PromptID)
|
|
}
|
|
return prompts
|
|
}
|
|
|
|
func repositoryPath(parts ...string) string {
|
|
_, file, _, _ := runtime.Caller(0)
|
|
return filepath.Join(append([]string{filepath.Dir(file), "..", ".."}, parts...)...)
|
|
}
|
|
|
|
func readRepositoryFile(t *testing.T, parts ...string) []byte {
|
|
t.Helper()
|
|
data, err := os.ReadFile(repositoryPath(parts...))
|
|
if err != nil {
|
|
t.Fatal(err)
|
|
}
|
|
return data
|
|
}
|