Organize D&D extensions by domain

This commit is contained in:
2026-07-17 05:05:48 +00:00
parent a81b9f1e1f
commit 15c369c509
64 changed files with 469 additions and 194 deletions

View File

@@ -0,0 +1,289 @@
package integration_test
import (
"context"
"os"
"strings"
"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/extract/spells"
"gitea.maximumdirect.net/eric/notarius/internal/modules/generic/merge/appendorder"
"gitea.maximumdirect.net/eric/notarius/internal/modules/generic/normalize/noop"
"gitea.maximumdirect.net/eric/notarius/internal/modules/seriatim/input/transcript"
)
func TestPipelineConfigLoadsAndResolvesWithDNDSpellsExtractor(t *testing.T) {
data, err := os.ReadFile("testdata/pipeline.yml")
if err != nil {
t.Fatalf("ReadFile(pipeline.yml) error = %v, want nil", err)
}
fileCfg, err := config.ParseFileConfigYAML(data)
if err != nil {
t.Fatalf("ParseFileConfigYAML() error = %v, want nil", err)
}
cfg := config.Default()
if err := cfg.ApplyFileConfig(fileCfg); err != nil {
t.Fatalf("ApplyFileConfig() error = %v, want nil", err)
}
resolved, err := cfg.Resolve(config.ResolveInput{
PipelineID: "dnd-spells-fixture",
Catalog: dndSpellsTestCatalog(t, dndSpellsCatalogSpecs{}),
})
if err != nil {
t.Fatalf("Resolve() error = %v, want nil", err)
}
if len(resolved.ResolvedPipeline.ArtifactLanes) != 1 {
t.Fatalf("len(ArtifactLanes) = %d, want 1", len(resolved.ResolvedPipeline.ArtifactLanes))
}
lane := resolved.ResolvedPipeline.ArtifactLanes[0]
if lane.ID != "spells" {
t.Fatalf("lane ID = %q, want spells", lane.ID)
}
if lane.Extract.Module != spells.Key {
t.Fatalf("extract module = %q, want %q", lane.Extract.Module, spells.Key)
}
if resolved.ResolvedPipeline.Digest == "" {
t.Fatal("resolved digest is empty")
}
again, err := cfg.Resolve(config.ResolveInput{
PipelineID: "dnd-spells-fixture",
Catalog: dndSpellsTestCatalog(t, dndSpellsCatalogSpecs{}),
})
if err != nil {
t.Fatalf("second Resolve() error = %v, want nil", err)
}
if resolved.ResolvedPipeline.Digest != again.ResolvedPipeline.Digest {
t.Fatalf("resolved digest = %q, second digest = %q; want stable digest", resolved.ResolvedPipeline.Digest, again.ResolvedPipeline.Digest)
}
}
func TestPipelineConfigRejectsMissingTranscriptCapabilityForDNDSpells(t *testing.T) {
inputSpec := transcript.ModuleSpec()
inputSpec.Provides = withoutCapability(inputSpec.Provides, "source.transcript")
chunkSpec := dndSpellsChunkerSpec()
chunkSpec.Requires = nil
_, err := loadDNDSpellsPipelineConfig(t).Resolve(config.ResolveInput{
PipelineID: "dnd-spells-fixture",
Catalog: dndSpellsTestCatalog(t, dndSpellsCatalogSpecs{
input: inputSpec,
chunk: chunkSpec,
}),
})
if err == nil {
t.Fatal("Resolve() error = nil, want missing capability error")
}
if !strings.Contains(err.Error(), "missing capability") ||
!strings.Contains(err.Error(), "source.transcript") ||
!strings.Contains(err.Error(), spells.Key) {
t.Fatalf("Resolve() error = %q, want dnd/spells missing source.transcript capability", err.Error())
}
}
func TestPipelineConfigRejectsMissingSpellCastsCapabilityForAppendOrder(t *testing.T) {
extractorSpec := spells.ModuleSpec()
extractorSpec.Provides = withoutCapability(extractorSpec.Provides, "dnd.spell_casts")
_, err := loadDNDSpellsPipelineConfig(t).Resolve(config.ResolveInput{
PipelineID: "dnd-spells-fixture",
Catalog: dndSpellsTestCatalog(t, dndSpellsCatalogSpecs{
extractor: extractorSpec,
}),
})
if err == nil {
t.Fatal("Resolve() error = nil, want missing capability error")
}
if !strings.Contains(err.Error(), "missing capability") ||
!strings.Contains(err.Error(), "dnd.spell_casts") ||
!strings.Contains(err.Error(), pipeline.DefaultMergeModule) {
t.Fatalf("Resolve() error = %q, want appendorder missing dnd.spell_casts capability", err.Error())
}
}
func TestPipelineConfigRejectsUnknownLaneSelection(t *testing.T) {
_, err := loadDNDSpellsPipelineConfig(t).Resolve(config.ResolveInput{
PipelineID: "dnd-spells-fixture",
Only: []string{"missing"},
Catalog: dndSpellsTestCatalog(t, dndSpellsCatalogSpecs{}),
})
if err == nil {
t.Fatal("Resolve() error = nil, want unknown lane error")
}
if !strings.Contains(err.Error(), "selected artifact lane") || !strings.Contains(err.Error(), "missing") {
t.Fatalf("Resolve() error = %q, want unknown lane context", err.Error())
}
}
func loadDNDSpellsPipelineConfig(t *testing.T) config.Config {
t.Helper()
data, err := os.ReadFile("testdata/pipeline.yml")
if err != nil {
t.Fatalf("ReadFile(pipeline.yml) error = %v, want nil", err)
}
fileCfg, err := config.ParseFileConfigYAML(data)
if err != nil {
t.Fatalf("ParseFileConfigYAML() error = %v, want nil", err)
}
cfg := config.Default()
if err := cfg.ApplyFileConfig(fileCfg); err != nil {
t.Fatalf("ApplyFileConfig() error = %v, want nil", err)
}
return cfg
}
type dndSpellsCatalogSpecs struct {
input pipeline.ModuleSpec
chunk pipeline.ModuleSpec
extractor pipeline.ModuleSpec
}
func dndSpellsTestCatalog(t *testing.T, specs dndSpellsCatalogSpecs) pipeline.ModuleCatalog {
t.Helper()
inputs := pipeline.NewInputAdapterRegistry()
chunkers := pipeline.NewChunkerRegistry()
extractors := pipeline.NewExtractorRegistry()
mergers := pipeline.NewMergerRegistry()
normalizers := pipeline.NewNormalizerRegistry()
outputs := pipeline.NewOutputEncoderRegistry()
if specs.input.Key == "" {
if err := transcript.Register(inputs); err != nil {
t.Fatalf("register seriatim input: %v", err)
}
} else if err := inputs.RegisterWithSpec(specs.input, func() (contracts.InputAdapter, error) {
return transcript.New(), nil
}); err != nil {
t.Fatalf("register seriatim input override: %v", err)
}
chunkSpec := specs.chunk
if chunkSpec.Key == "" {
chunkSpec = dndSpellsChunkerSpec()
}
if err := chunkers.RegisterWithSpec(chunkSpec, func() (contracts.Chunker, error) {
return dndSpellsChunker{}, nil
}); err != nil {
t.Fatalf("register chunker: %v", err)
}
if specs.extractor.Key == "" {
if err := spells.Register(extractors); err != nil {
t.Fatalf("register dnd spells extractor: %v", err)
}
} else if err := extractors.RegisterWithSpec(specs.extractor, func() (contracts.Extractor, error) {
return spells.New(), nil
}); err != nil {
t.Fatalf("register dnd spells extractor override: %v", err)
}
if err := mergers.RegisterWithSpec(pipeline.ModuleSpec{
Key: pipeline.DefaultMergeModule,
Stage: pipeline.StageMerge,
Requires: []string{"dnd.spell_casts"},
}, func() (contracts.Merger, error) {
return appendorder.New(), nil
}); err != nil {
t.Fatalf("register merger: %v", err)
}
if err := normalizers.RegisterWithSpec(pipeline.ModuleSpec{
Key: pipeline.DefaultNormalizeModule,
Stage: pipeline.StageNormalize,
}, func() (contracts.Normalizer, error) {
return noop.New(), nil
}); err != nil {
t.Fatalf("register normalizer: %v", err)
}
if err := outputs.RegisterWithSpec(pipeline.ModuleSpec{
Key: pipeline.DefaultOutputModule,
Stage: pipeline.StageOutput,
}, func() (contracts.OutputEncoder, error) {
return dndSpellsOutput{}, nil
}); err != nil {
t.Fatalf("register output: %v", err)
}
return pipeline.ModuleCatalog{
Inputs: inputs,
Chunkers: chunkers,
Extractors: extractors,
Mergers: mergers,
Normalizers: normalizers,
ValidatorChains: pipeline.NewValidatorChainRegistry(),
Outputs: outputs,
}
}
func dndSpellsChunkerSpec() pipeline.ModuleSpec {
return pipeline.ModuleSpec{
Key: "fake/chunk",
Stage: pipeline.StageChunk,
Requires: []string{"source.transcript"},
Provides: []string{"chunks"},
}
}
type dndSpellsChunker struct{}
func (dndSpellsChunker) Key() string {
return "fake/chunk"
}
func (dndSpellsChunker) ReferenceSlots() []contracts.ReferenceSlot {
return nil
}
func (dndSpellsChunker) Chunk(ctx context.Context, req contracts.ChunkRequest) (contracts.ChunkResult, error) {
return contracts.ChunkResult{
Chunks: []contracts.SourceChunk{
{
ID: req.Source.ID + ":chunk:0",
SourceID: req.Source.ID,
Index: 0,
StartUnitID: req.Source.Units[0].ID,
EndUnitID: req.Source.Units[len(req.Source.Units)-1].ID,
Content: []byte(`{"units":[1,2,3]}`),
MediaType: "application/json",
Units: append([]source.SourceUnit(nil), req.Source.Units...),
},
},
}, nil
}
type dndSpellsOutput struct{}
func (dndSpellsOutput) Key() string {
return pipeline.DefaultOutputModule
}
func (dndSpellsOutput) Encode(ctx context.Context, req contracts.OutputRequest) (contracts.OutputResult, error) {
return contracts.OutputResult{
Files: []contracts.OutputFile{
{Name: "output.json", ContentType: "application/json", Bytes: []byte(`{"encoded":true}`)},
},
}, nil
}
func withoutCapability(capabilities []string, capability string) []string {
filtered := make([]string, 0, len(capabilities))
for _, candidate := range capabilities {
if candidate != capability {
filtered = append(filtered, candidate)
}
}
return filtered
}
var (
_ contracts.Chunker = dndSpellsChunker{}
_ contracts.OutputEncoder = dndSpellsOutput{}
)

View File

@@ -0,0 +1,63 @@
package integration_test
import (
"context"
"encoding/json"
"fmt"
"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared"
)
type extractionResponse struct {
SpellCasts []spellCastResponse `json:"spell_casts"`
}
type spellCastResponse struct {
Caster string `json:"caster"`
Spell string `json:"spell"`
Effect string `json:"effect"`
NarrativeDescription string `json:"narrative_description"`
SourceRefs []shared.SourceRefResponse `json:"source_refs"`
}
type fakeSpellsLLMClient struct {
response extractionResponse
requests []contracts.StructuredCompletionRequest
}
func (client *fakeSpellsLLMClient) CompleteStructured(_ context.Context, req contracts.StructuredCompletionRequest, out any) (contracts.StructuredCompletionResponse, error) {
client.requests = append(client.requests, cloneStructuredCompletionRequest(req))
content, err := json.Marshal(client.response)
if err != nil {
return contracts.StructuredCompletionResponse{}, err
}
if err := json.Unmarshal(content, out); err != nil {
return contracts.StructuredCompletionResponse{}, fmt.Errorf("populate structured target: %w", err)
}
return contracts.StructuredCompletionResponse{Content: content}, nil
}
func responseSourceRefs(sourceID string, startUnitID int, endUnitID int) []shared.SourceRefResponse {
return []shared.SourceRefResponse{
{
SourceID: sourceID,
StartUnitID: shared.UnitRefFromInt(startUnitID),
EndUnitID: shared.UnitRefFromInt(endUnitID),
},
}
}
func cloneStructuredCompletionRequest(req contracts.StructuredCompletionRequest) contracts.StructuredCompletionRequest {
req.Inputs = req.Inputs.Clone()
if len(req.Vars) == 0 {
req.Vars = nil
return req
}
vars := make(map[string]any, len(req.Vars))
for key, value := range req.Vars {
vars[key] = value
}
req.Vars = vars
return req
}

View File

@@ -0,0 +1,362 @@
package integration_test
import (
"context"
"encoding/json"
"os"
"strings"
"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/extract/spells"
"gitea.maximumdirect.net/eric/notarius/internal/modules/seriatim/input/transcript"
)
func TestRunnerProcessesSeriatimInputWithDNDSpellsExtractor(t *testing.T) {
raw := readDNDSpellsFixture(t)
expectedDoc := parseDNDSpellsFixture(t, raw)
resolved := resolveDNDSpellsPipeline(t)
llmClient := &fakeSpellsLLMClient{
response: extractionResponse{
SpellCasts: []spellCastResponse{
{
Caster: "Aria",
Spell: "Cure Wounds",
Effect: "Heals an injured ally.",
NarrativeDescription: "Aria restores the fighter after the fight.",
SourceRefs: responseSourceRefs(expectedDoc.ID, 1, 1),
},
{
Caster: "Borin",
Spell: "Fire Bolt",
Effect: "Scorches the wight.",
NarrativeDescription: "Borin hurls fire at the wight.",
SourceRefs: responseSourceRefs(expectedDoc.ID, 3, 3),
},
},
},
}
output, err := pipeline.New(dndSpellsRunnerRegistries(t)).Run(context.Background(), pipeline.RunInput{
Pipeline: resolved.ResolvedPipeline,
RawInput: raw,
LLMClient: llmClient,
})
if err != nil {
t.Fatalf("Run() error = %v, want nil", err)
}
if len(output.NormalizeOutputs) != 1 {
t.Fatalf("len(NormalizeOutputs) = %d, want 1", len(output.NormalizeOutputs))
}
rawOutput := output.NormalizeOutputs[0]
if rawOutput.LaneID != "spells" || rawOutput.Schema.ID != spells.ResponseSchemaID || rawOutput.Schema.Version != spells.SchemaVersion {
t.Fatalf("raw output envelope = %#v, want dnd spells schema on spells lane", rawOutput)
}
response := decodeRunnerSpellResponse(t, rawOutput.Payload.Content)
if len(response.SpellCasts) != 2 {
t.Fatalf("len(spell_casts) = %d, want 2", len(response.SpellCasts))
}
first, second := response.SpellCasts[0], response.SpellCasts[1]
if first.Spell != "Cure Wounds" || second.Spell != "Fire Bolt" {
t.Fatalf("spell order = %q, %q; want source-unit order", first.Spell, second.Spell)
}
if first.Caster != "Aria" || second.Caster != "Borin" {
t.Fatalf("casters = %q, %q; want spell data", first.Caster, second.Caster)
}
for _, spell := range response.SpellCasts {
if len(spell.SourceRefs) != 1 {
t.Fatalf("len(SourceRefs) = %d, want 1", len(spell.SourceRefs))
}
if spell.SourceRefs[0].SourceID != expectedDoc.ID {
t.Fatalf("SourceID = %q, want fixture document ID", spell.SourceRefs[0].SourceID)
}
}
if output.Manifest.InputModule != transcript.Key {
t.Fatalf("manifest input module = %q, want %q", output.Manifest.InputModule, transcript.Key)
}
if output.Manifest.ValidationStatus != "approved" {
t.Fatalf("ValidationStatus = %q, want approved", output.Manifest.ValidationStatus)
}
if len(output.Manifest.ArtifactLanes) != 1 {
t.Fatalf("len(ArtifactLanes) = %d, want 1", len(output.Manifest.ArtifactLanes))
}
lane := output.Manifest.ArtifactLanes[0]
if lane.ID != "spells" || lane.Extractor != spells.Key {
t.Fatalf("manifest lane = %#v, want spells lane with dnd/spells extractor", lane)
}
extractorMetadata, ok := lane.Metadata["extractor"].(map[string]any)
if !ok {
t.Fatalf("manifest lane metadata = %#v, want extractor metadata", lane.Metadata)
}
if extractorMetadata["prompt_id"] != spells.PromptID ||
extractorMetadata["response_schema_key"] != string(spells.ResponseSchemaKey) ||
extractorMetadata["response_schema_name"] != spells.ResponseSchemaName {
t.Fatalf("extractor metadata = %#v, want prompt/schema identifiers", extractorMetadata)
}
if len(output.OutputFiles) != 1 {
t.Fatalf("len(OutputFiles) = %d, want 1", len(output.OutputFiles))
}
if output.OutputFiles[0].ContentType != "application/json" {
t.Fatalf("ContentType = %q, want application/json", output.OutputFiles[0].ContentType)
}
}
func TestRunnerPassesPartyAndGlossaryReferencesToDNDSpellsPrompt(t *testing.T) {
raw := readDNDSpellsFixture(t)
expectedDoc := parseDNDSpellsFixture(t, raw)
resolved := resolveDNDSpellsPipeline(t)
resolved.ResolvedPipeline.ArtifactLanes[0].ExtractReferences.ReferenceSet = dndSpellsReferenceSet(
"Aria: party cleric\nBorin: fighter",
"Fire Bolt: evocation cantrip",
)
llmClient := &fakeSpellsLLMClient{
response: extractionResponse{
SpellCasts: []spellCastResponse{
{
Caster: "Borin",
Spell: "Fire Bolt",
Effect: "Scorches the wight.",
NarrativeDescription: "Borin hurls fire at the wight.",
SourceRefs: responseSourceRefs(expectedDoc.ID, 3, 3),
},
},
},
}
output, err := pipeline.New(dndSpellsRunnerRegistries(t)).Run(context.Background(), pipeline.RunInput{
Pipeline: resolved.ResolvedPipeline,
RawInput: raw,
LLMClient: llmClient,
})
if err != nil {
t.Fatalf("Run() error = %v, want nil", err)
}
if len(output.NormalizeOutputs) != 1 {
t.Fatalf("len(NormalizeOutputs) = %d, want 1", len(output.NormalizeOutputs))
}
if len(output.Manifest.References) != 2 {
t.Fatalf("manifest references = %#v, want party and glossary provenance", output.Manifest.References)
}
if len(llmClient.requests) != 1 {
t.Fatalf("LLM calls = %d, want 1", len(llmClient.requests))
}
request := llmClient.requests[0]
if request.PromptID != spells.PromptID || request.PromptVersion != spells.SchemaVersion {
t.Fatalf("prompt = %q/%q, want %q/%q", request.PromptID, request.PromptVersion, spells.PromptID, spells.SchemaVersion)
}
if got := string(request.Inputs["party"].Content); got != "Aria: party cleric\nBorin: fighter" {
t.Fatalf("party input = %q, want reference text", got)
}
if got := string(request.Inputs["glossary"].Content); got != "Fire Bolt: evocation cantrip" {
t.Fatalf("glossary input = %q, want reference text", got)
}
}
func TestRunnerDoesNotExtractSpellMentionedOnlyInPartyReference(t *testing.T) {
raw := readDNDSpellsFixture(t)
resolved := resolveDNDSpellsPipeline(t)
resolved.ResolvedPipeline.ArtifactLanes[0].ExtractReferences.ReferenceSet = dndSpellsReferenceSet(
"Mira: wizard who can cast Lightning Bolt",
"",
)
llmClient := &fakeSpellsLLMClient{
response: extractionResponse{SpellCasts: []spellCastResponse{}},
}
output, err := pipeline.New(dndSpellsRunnerRegistries(t)).Run(context.Background(), pipeline.RunInput{
Pipeline: resolved.ResolvedPipeline,
RawInput: raw,
LLMClient: llmClient,
})
if err != nil {
t.Fatalf("Run() error = %v, want nil", err)
}
if len(output.NormalizeOutputs) != 1 {
t.Fatalf("len(NormalizeOutputs) = %d, want empty spell response output", len(output.NormalizeOutputs))
}
response := decodeRunnerSpellResponse(t, output.NormalizeOutputs[0].Payload.Content)
if len(response.SpellCasts) != 0 {
t.Fatalf("spell_casts = %#v, want no party-reference-only spell casts", response.SpellCasts)
}
if len(llmClient.requests) != 1 {
t.Fatalf("LLM calls = %d, want 1", len(llmClient.requests))
}
request := llmClient.requests[0]
if request.PromptID != spells.PromptID || request.PromptVersion != spells.SchemaVersion {
t.Fatalf("prompt = %q/%q, want %q/%q", request.PromptID, request.PromptVersion, spells.PromptID, spells.SchemaVersion)
}
if got := string(request.Inputs["party"].Content); !strings.Contains(got, "Lightning Bolt") {
t.Fatalf("party input = %q, want party-reference-only spell in reference input", got)
}
if output.Manifest.ValidationStatus != "approved" {
t.Fatalf("ValidationStatus = %q, want approved empty extraction", output.Manifest.ValidationStatus)
}
}
func TestRunnerCarriesDNDSpellCastWithInvalidSourceRefAsRawOutput(t *testing.T) {
raw := readDNDSpellsFixture(t)
resolved := resolveDNDSpellsPipeline(t)
llmClient := &fakeSpellsLLMClient{
response: extractionResponse{
SpellCasts: []spellCastResponse{
{
Caster: "Aria",
Spell: "Cure Wounds",
Effect: "Heals an injured ally.",
NarrativeDescription: "Aria restores the fighter after the fight.",
SourceRefs: responseSourceRefs("spell-session", 999, 999),
},
},
},
}
output, err := pipeline.New(dndSpellsRunnerRegistries(t)).Run(context.Background(), pipeline.RunInput{
Pipeline: resolved.ResolvedPipeline,
RawInput: raw,
LLMClient: llmClient,
})
if err != nil {
t.Fatalf("Run() error = %v, want nil", err)
}
if len(output.NormalizeOutputs) != 1 {
t.Fatalf("len(NormalizeOutputs) = %d, want 1", len(output.NormalizeOutputs))
}
response := decodeRunnerSpellResponse(t, output.NormalizeOutputs[0].Payload.Content)
if len(response.SpellCasts) != 1 {
t.Fatalf("len(spell_casts) = %d, want 1", len(response.SpellCasts))
}
if response.SpellCasts[0].SourceRefs[0].SourceID != "spell-session" {
t.Fatalf("SourceID = %q, want raw invalid source ref preserved", response.SpellCasts[0].SourceRefs[0].SourceID)
}
if len(output.Rejected) != 0 {
t.Fatalf("len(Rejected) = %d, want 0", len(output.Rejected))
}
if output.Manifest.ValidationStatus != "approved" {
t.Fatalf("ValidationStatus = %q, want approved", output.Manifest.ValidationStatus)
}
}
func dndSpellsReferenceSet(party string, glossary string) contracts.ReferenceSet {
slots := make(map[string]contracts.ResolvedReferenceSlot)
if strings.TrimSpace(party) != "" {
slots["party"] = contracts.ResolvedReferenceSlot{
Slot: contracts.ReferenceSlot{Name: "party"},
Items: []contracts.ReferenceItem{
{
SlotName: "party",
MediaType: "text/plain; charset=utf-8",
Content: []byte(party),
Digest: "sha256:party",
Origin: contracts.ReferenceOrigin{Type: "file", URI: "file:///tmp/party.txt"},
SizeBytes: int64(len(party)),
BindingSource: contracts.ReferenceBindingSourceConfig,
},
},
}
}
if strings.TrimSpace(glossary) != "" {
slots["glossary"] = contracts.ResolvedReferenceSlot{
Slot: contracts.ReferenceSlot{Name: "glossary"},
Items: []contracts.ReferenceItem{
{
SlotName: "glossary",
MediaType: "text/plain; charset=utf-8",
Content: []byte(glossary),
Digest: "sha256:glossary",
Origin: contracts.ReferenceOrigin{Type: "file", URI: "file:///tmp/glossary.txt"},
SizeBytes: int64(len(glossary)),
BindingSource: contracts.ReferenceBindingSourceConfig,
},
},
}
}
return contracts.ReferenceSet{Slots: slots}
}
func TestRunnerCarriesMalformedDNDSpellsExtractorOutput(t *testing.T) {
raw := readDNDSpellsFixture(t)
resolved := resolveDNDSpellsPipeline(t)
llmClient := &fakeSpellsLLMClient{response: extractionResponse{}}
output, err := pipeline.New(dndSpellsRunnerRegistries(t)).Run(context.Background(), pipeline.RunInput{
Pipeline: resolved.ResolvedPipeline,
RawInput: raw,
LLMClient: llmClient,
})
if err != nil {
t.Fatalf("Run() error = %v, want nil", err)
}
if len(output.NormalizeOutputs) != 1 {
t.Fatalf("len(NormalizeOutputs) = %d, want raw output", len(output.NormalizeOutputs))
}
if string(output.NormalizeOutputs[0].Payload.Content) != `{"spell_casts":null}` {
t.Fatalf("content = %s, want canonical structured output", output.NormalizeOutputs[0].Payload.Content)
}
if output.Manifest.ValidationStatus != "approved" {
t.Fatalf("ValidationStatus = %q, want approved", output.Manifest.ValidationStatus)
}
}
func resolveDNDSpellsPipeline(t *testing.T) config.EffectiveConfig {
t.Helper()
resolved, err := loadDNDSpellsPipelineConfig(t).Resolve(config.ResolveInput{
PipelineID: "dnd-spells-fixture",
Catalog: dndSpellsTestCatalog(t, dndSpellsCatalogSpecs{}),
})
if err != nil {
t.Fatalf("Resolve() error = %v, want nil", err)
}
return resolved
}
func dndSpellsRunnerRegistries(t *testing.T) pipeline.Registries {
t.Helper()
catalog := dndSpellsTestCatalog(t, dndSpellsCatalogSpecs{})
return pipeline.Registries{
Inputs: catalog.Inputs,
Chunkers: catalog.Chunkers,
Extractors: catalog.Extractors,
Mergers: catalog.Mergers,
Normalizers: catalog.Normalizers,
Outputs: catalog.Outputs,
}
}
func readDNDSpellsFixture(t *testing.T) []byte {
t.Helper()
raw, err := os.ReadFile("testdata/seriatim_spell_session.json")
if err != nil {
t.Fatalf("ReadFile(seriatim_spell_session.json) error = %v, want nil", err)
}
return raw
}
func parseDNDSpellsFixture(t *testing.T, raw []byte) *source.SourceDocument {
t.Helper()
doc, err := transcript.New().Parse(context.Background(), contracts.ParseRequest{Raw: raw})
if err != nil {
t.Fatalf("Parse() error = %v, want nil", err)
}
return doc
}
func decodeRunnerSpellResponse(t *testing.T, raw []byte) extractionResponse {
t.Helper()
var response extractionResponse
if err := json.Unmarshal(raw, &response); err != nil {
t.Fatalf("Unmarshal(raw output) error = %v, want nil", err)
}
return response
}

View File

@@ -0,0 +1,11 @@
version: 2
pipelines:
dnd-spells-fixture:
input: seriatim
chunk: fake/chunk
artifacts:
spells:
extract: dnd/spells
merge: appendorder
normalize: noop
output: json

View File

@@ -0,0 +1,29 @@
{
"metadata": {
"id": "spell-session",
"title": "Synthetic D&D spell session"
},
"segments": [
{
"id": 1,
"start": 0,
"end": 4,
"speaker": "Alice",
"text": "Aria raises her holy symbol and casts Cure Wounds."
},
{
"id": 2,
"start": 4,
"end": 8,
"speaker": "DM",
"text": "The bandit mage casts Shield as the blow lands."
},
{
"id": 3,
"start": 8,
"end": 12,
"speaker": "Bob",
"text": "Borin points at the wight and casts Fire Bolt."
}
]
}