326 lines
12 KiB
Go
326 lines
12 KiB
Go
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"
|
|
spellcodec "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/codec/spells"
|
|
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/extract/spells"
|
|
spellnormalize "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/normalize/spells"
|
|
spellshape "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/spells/shape"
|
|
spellsourcerefs "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/spells/source_refs"
|
|
"gitea.maximumdirect.net/eric/notarius/internal/modules/seriatim/input/transcript"
|
|
)
|
|
|
|
func runPreparedPipeline(t *testing.T, registries pipeline.Registries, resolved pipeline.ResolvedPipeline, llmClient contracts.StructuredLLMClient, input pipeline.RunInput) (pipeline.RunOutput, error) {
|
|
t.Helper()
|
|
prepared, err := pipeline.Prepare(resolved, registries, pipeline.ModuleDependencies{LLM: llmClient})
|
|
if err != nil {
|
|
return pipeline.RunOutput{}, err
|
|
}
|
|
input.Prepared = prepared
|
|
return pipeline.New().Run(context.Background(), input)
|
|
}
|
|
|
|
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",
|
|
SourceRefs: responseSourceRefs(1, 1),
|
|
},
|
|
{
|
|
Caster: "Borin",
|
|
Spell: "Fire Bolt",
|
|
SourceRefs: responseSourceRefs(3, 3),
|
|
},
|
|
},
|
|
},
|
|
}
|
|
|
|
output, err := runPreparedPipeline(t, dndSpellsRunnerRegistries(t), resolved.ResolvedPipeline, llmClient, pipeline.RunInput{
|
|
RawInput: raw,
|
|
})
|
|
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))
|
|
}
|
|
serializedOutput := output.NormalizeOutputs[0]
|
|
if serializedOutput.LaneID != "spells" || serializedOutput.Artifact.Schema.ID != spells.ResponseSchemaID || serializedOutput.Artifact.Schema.Version != spells.SchemaVersion {
|
|
t.Fatalf("serialized output envelope = %#v, want dnd spells schema on spells lane", serializedOutput)
|
|
}
|
|
response := decodeRunnerSpellResponse(t, serializedOutput.Artifact.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)
|
|
resolved := resolveDNDSpellsPipeline(t)
|
|
resolved.ResolvedPipeline.Steps[0].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",
|
|
SourceRefs: responseSourceRefs(3, 3),
|
|
},
|
|
},
|
|
},
|
|
}
|
|
|
|
output, err := runPreparedPipeline(t, dndSpellsRunnerRegistries(t), resolved.ResolvedPipeline, llmClient, pipeline.RunInput{
|
|
RawInput: raw,
|
|
})
|
|
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 TestProductionSpellPipelineRoutesSemanticCandidatesToDeterministicValidators(t *testing.T) {
|
|
registries := productionNPCRegistries(t)
|
|
configValue := config.Default()
|
|
configValue.Pipelines["dnd-spells-shape"] = pipeline.PipelineProfile{
|
|
Input: pipeline.Binding(transcript.Key),
|
|
Chunk: pipeline.ModuleBinding{Module: pipeline.DefaultChunkModule, Options: map[string]any{"max_units": 100}},
|
|
Artifacts: map[string]pipeline.ArtifactLaneProfile{
|
|
"spells": {
|
|
Extract: pipeline.ModuleBinding{Module: spells.Key, Retries: 2},
|
|
Normalize: pipeline.Binding(spellnormalize.Key),
|
|
},
|
|
},
|
|
}
|
|
effective, err := configValue.Resolve(config.ResolveInput{
|
|
PipelineID: "dnd-spells-shape",
|
|
Catalog: moduleCatalog(registries),
|
|
})
|
|
if err != nil {
|
|
t.Fatalf("Resolve() error = %v, want nil", err)
|
|
}
|
|
for _, test := range []struct {
|
|
name string
|
|
response []byte
|
|
reasonCode string
|
|
validatorName string
|
|
}{
|
|
{
|
|
name: "blank string",
|
|
response: []byte(`{"spell_casts":[{"caster":"","spell":"Cure Wounds","source_refs":[{"start_unit_id":1,"end_unit_id":1}]}]}`),
|
|
reasonCode: spellshape.ReasonCode,
|
|
validatorName: spellshape.Key,
|
|
},
|
|
{
|
|
name: "empty evidence",
|
|
response: []byte(`{"spell_casts":[{"caster":"Aria","spell":"Cure Wounds","source_refs":[]}]}`),
|
|
reasonCode: spellshape.ReasonCode,
|
|
validatorName: spellshape.Key,
|
|
},
|
|
{
|
|
name: "nonpositive unit candidate",
|
|
response: []byte(`{"spell_casts":[{"caster":"Aria","spell":"Cure Wounds","source_refs":[{"start_unit_id":0,"end_unit_id":1}]}]}`),
|
|
reasonCode: spellsourcerefs.ReasonCode,
|
|
validatorName: spellsourcerefs.Key,
|
|
},
|
|
{
|
|
name: "unknown unit candidate",
|
|
response: []byte(`{"spell_casts":[{"caster":"Aria","spell":"Cure Wounds","source_refs":[{"start_unit_id":99,"end_unit_id":99}]}]}`),
|
|
reasonCode: spellsourcerefs.ReasonCode,
|
|
validatorName: spellsourcerefs.Key,
|
|
},
|
|
} {
|
|
t.Run(test.name, func(t *testing.T) {
|
|
client := &fakeSpellsLLMClient{rawResponses: [][]byte{test.response, test.response, test.response}}
|
|
output, err := runPreparedPipeline(t, registries, effective.ResolvedPipeline, client, pipeline.RunInput{RawInput: readDNDSpellsFixture(t)})
|
|
if err != nil {
|
|
t.Fatalf("Run() error = %v, want non-fatal rejected output", err)
|
|
}
|
|
if len(client.requests) != 3 || len(output.Rejected) != 1 || len(output.NormalizeOutputs) != 0 {
|
|
t.Fatalf("LLM requests = %d rejected = %#v normalized = %#v, want exhausted rejection", len(client.requests), output.Rejected, output.NormalizeOutputs)
|
|
}
|
|
rejection := output.Rejected[0]
|
|
if rejection.ReasonCode != test.reasonCode || rejection.ValidatorName != test.validatorName || rejection.AttemptCount != 3 {
|
|
t.Fatalf("rejection = %#v, want exhausted %s rejection", rejection, test.validatorName)
|
|
}
|
|
})
|
|
}
|
|
}
|
|
|
|
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 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,
|
|
ArtifactCodecs: catalog.ArtifactCodecs,
|
|
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) dnd.SpellList {
|
|
t.Helper()
|
|
|
|
response, err := spellcodec.New().Decode(raw)
|
|
if err != nil {
|
|
t.Fatalf("decode durable spell output: %v", err)
|
|
}
|
|
return response
|
|
}
|