Files
notarius/internal/framework/pipeline/walking_skeleton_test.go

463 lines
14 KiB
Go

package pipeline
import (
"context"
"crypto/sha256"
"encoding/hex"
"encoding/json"
"fmt"
"os"
"reflect"
"strings"
"testing"
"gitea.maximumdirect.net/eric/notarius/internal/core/artifacts"
"gitea.maximumdirect.net/eric/notarius/internal/core/source"
"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
)
func TestWalkingSkeletonFixture(t *testing.T) {
inputBytes := readTestFixture(t, "testdata/walking_skeleton_input.json")
expectedBytes := readTestFixture(t, "testdata/walking_skeleton_output.json")
llmClient := &walkingSkeletonLLMClient{}
resolved, err := ResolvePipeline(walkingSkeletonProfile(), ResolveOptions{}, walkingSkeletonCatalog(t))
if err != nil {
t.Fatalf("ResolvePipeline() error = %v, want nil", err)
}
output, err := New(walkingSkeletonRegistries(t)).Run(context.Background(), RunInput{
Pipeline: resolved,
SourceID: "fixture-source",
Path: "walking_skeleton_input.json",
RawInput: inputBytes,
LLMClient: llmClient,
})
if err != nil {
t.Fatalf("Run() error = %v, want nil", err)
}
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)
}
assertStructuralJSONEqual(t, output.OutputFiles[0].Bytes, expectedBytes)
if llmClient.calls != 3 {
t.Fatalf("LLM calls = %d, want extractor calls plus normalizer call", llmClient.calls)
}
}
func TestWalkingSkeletonResolutionRejectsMissingCapability(t *testing.T) {
catalog := walkingSkeletonCatalog(t)
catalog.Extractors = NewExtractorRegistry()
if err := catalog.Extractors.RegisterWithSpec(ModuleSpec{
Key: "fake/extract",
Stage: StageExtract,
Requires: []string{"missing"},
Provides: []string{"fake_artifacts"},
}, func() (contracts.Extractor, error) {
return walkingSkeletonExtractor{}, nil
}); err != nil {
t.Fatalf("RegisterWithSpec() error = %v, want nil", err)
}
_, err := ResolvePipeline(walkingSkeletonProfile(), ResolveOptions{}, catalog)
if err == nil {
t.Fatal("ResolvePipeline() error = nil, want error")
}
if !strings.Contains(err.Error(), "missing") {
t.Fatalf("ResolvePipeline() error = %q, want missing capability", err.Error())
}
}
func TestWalkingSkeletonResolutionRejectsUnknownOnlyLane(t *testing.T) {
_, err := ResolvePipeline(walkingSkeletonProfile(), ResolveOptions{Only: []string{"missing"}}, walkingSkeletonCatalog(t))
if err == nil {
t.Fatal("ResolvePipeline() error = nil, want error")
}
if !strings.Contains(err.Error(), "missing") || !strings.Contains(err.Error(), "not declared") {
t.Fatalf("ResolvePipeline() error = %q, want unknown lane error", err.Error())
}
}
func walkingSkeletonProfile() PipelineProfile {
return PipelineProfile{
ID: "walking-skeleton",
Input: Binding("fake/input"),
Chunk: Binding("fake/chunk"),
Output: Binding("json"),
Artifacts: map[string]ArtifactLaneProfile{
"events": {Extract: Binding("fake/extract")},
},
}
}
func walkingSkeletonCatalog(t *testing.T) ModuleCatalog {
t.Helper()
catalog := ModuleCatalog{
Inputs: NewInputAdapterRegistry(),
Chunkers: NewChunkerRegistry(),
Extractors: NewExtractorRegistry(),
Mergers: NewMergerRegistry(),
Normalizers: NewNormalizerRegistry(),
ValidatorChains: NewValidatorChainRegistry(),
Outputs: NewOutputEncoderRegistry(),
}
if err := catalog.Inputs.RegisterWithSpec(ModuleSpec{
Key: "fake/input",
Stage: StageInput,
Provides: []string{"plain_text"},
}, func() (contracts.InputAdapter, error) {
return walkingSkeletonInput{}, nil
}); err != nil {
t.Fatalf("register fake input: %v", err)
}
if err := catalog.Chunkers.RegisterWithSpec(ModuleSpec{
Key: "fake/chunk",
Stage: StageChunk,
Requires: []string{"plain_text"},
Provides: []string{"chunks"},
}, func() (contracts.Chunker, error) {
return walkingSkeletonChunker{}, nil
}); err != nil {
t.Fatalf("register fake chunker: %v", err)
}
if err := catalog.Extractors.RegisterWithSpec(ModuleSpec{
Key: "fake/extract",
Stage: StageExtract,
Requires: []string{"chunks"},
Provides: []string{"fake_artifacts"},
}, func() (contracts.Extractor, error) {
return walkingSkeletonExtractor{}, nil
}); err != nil {
t.Fatalf("register fake extractor: %v", err)
}
if err := catalog.Mergers.RegisterWithSpec(ModuleSpec{
Key: DefaultMergeModule,
Stage: StageMerge,
Requires: []string{"fake_artifacts"},
}, func() (contracts.Merger, error) {
return walkingSkeletonMerger{}, nil
}); err != nil {
t.Fatalf("register append-order merger: %v", err)
}
if err := catalog.Normalizers.RegisterWithSpec(ModuleSpec{
Key: DefaultNormalizeModule,
Stage: StageNormalize,
}, func() (contracts.Normalizer, error) {
return walkingSkeletonNormalizer{}, nil
}); err != nil {
t.Fatalf("register no-op normalizer: %v", err)
}
if err := catalog.Outputs.RegisterWithSpec(ModuleSpec{
Key: "json",
Stage: StageOutput,
}, func() (contracts.OutputEncoder, error) {
return walkingSkeletonOutput{}, nil
}); err != nil {
t.Fatalf("register fake output: %v", err)
}
return catalog
}
func walkingSkeletonRegistries(t *testing.T) Registries {
t.Helper()
catalog := walkingSkeletonCatalog(t)
return Registries{
Inputs: catalog.Inputs,
Chunkers: catalog.Chunkers,
Extractors: catalog.Extractors,
Mergers: catalog.Mergers,
Normalizers: catalog.Normalizers,
Outputs: catalog.Outputs,
}
}
type walkingSkeletonInput struct{}
func (input walkingSkeletonInput) Key() string {
return "fake/input"
}
func (input walkingSkeletonInput) Parse(ctx context.Context, req contracts.ParseRequest) (*source.SourceDocument, error) {
var fixture struct {
ID string `json:"id"`
Units []struct {
ID int `json:"id"`
Text string `json:"text"`
} `json:"units"`
}
if err := json.Unmarshal(req.Raw, &fixture); err != nil {
return nil, err
}
units := make([]source.SourceUnit, 0, len(fixture.Units))
for _, unit := range fixture.Units {
units = append(units, source.SourceUnit{
ID: unit.ID,
Kind: "unit",
Text: unit.Text,
})
}
return &source.SourceDocument{
ID: fixture.ID,
Kind: "fixture",
Format: "application/json",
Digest: rawDigest(req.Raw),
Units: units,
}, nil
}
type walkingSkeletonChunker struct{}
func (chunker walkingSkeletonChunker) Key() string {
return "fake/chunk"
}
func (chunker walkingSkeletonChunker) ReferenceSlots() []contracts.ReferenceSlot {
return nil
}
func (chunker walkingSkeletonChunker) Chunk(ctx context.Context, req contracts.ChunkRequest) (contracts.ChunkResult, error) {
if len(req.Source.Units) < 3 {
return contracts.ChunkResult{}, fmt.Errorf("fixture source must contain at least three units")
}
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[1].ID,
Content: []byte(`{"units":[1,2]}`),
MediaType: "application/json",
Units: append([]source.SourceUnit(nil), req.Source.Units[:2]...),
},
{
ID: req.Source.ID + ":chunk:1",
SourceID: req.Source.ID,
Index: 1,
StartUnitID: req.Source.Units[2].ID,
EndUnitID: req.Source.Units[len(req.Source.Units)-1].ID,
Content: []byte(`{"units":[3]}`),
MediaType: "application/json",
Units: append([]source.SourceUnit(nil), req.Source.Units[2:]...),
},
},
}, nil
}
type walkingSkeletonExtractor struct{}
func (extractor walkingSkeletonExtractor) Key() string {
return "fake/extract"
}
func (extractor walkingSkeletonExtractor) ReferenceSlots() []contracts.ReferenceSlot {
return nil
}
func (extractor walkingSkeletonExtractor) Extract(ctx context.Context, req contracts.ExtractionRequest) (contracts.ExtractionResult, error) {
var response struct {
Call int `json:"call"`
}
if _, err := req.LLMClient.CompleteStructured(ctx, contracts.StructuredCompletionRequest{
StageName: "fake/extract",
PromptID: "fake.event",
PromptVersion: "v1",
}, &response); err != nil {
return contracts.ExtractionResult{}, err
}
payload, err := json.Marshal(map[string]any{
"chunk_id": req.Chunk.ID,
"llm_call": response.Call,
"text": chunkText(req.Chunk.Units),
})
if err != nil {
return contracts.ExtractionResult{}, err
}
return contracts.ExtractionResult{
Output: contracts.ExtractOutput{
Schema: contracts.ResponseSchema{ID: "fake_event", Name: "fake_event", Version: "v1"},
Payload: contracts.RawPayload{
Content: payload,
MediaType: "application/json",
},
},
}, nil
}
type walkingSkeletonLLMClient struct {
calls int
}
func (client *walkingSkeletonLLMClient) CompleteStructured(ctx context.Context, req contracts.StructuredCompletionRequest, out any) (contracts.StructuredCompletionResponse, error) {
client.calls++
if response, ok := out.(*struct {
Call int `json:"call"`
}); ok {
response.Call = client.calls
}
content, err := json.Marshal(map[string]any{"call": client.calls})
if err != nil {
return contracts.StructuredCompletionResponse{}, err
}
return contracts.StructuredCompletionResponse{
Content: content,
}, nil
}
type walkingSkeletonMerger struct{}
func (merger walkingSkeletonMerger) Key() string {
return DefaultMergeModule
}
func (merger walkingSkeletonMerger) Merge(ctx context.Context, req contracts.MergeRequest) (contracts.MergeResult, error) {
outputs := make([]json.RawMessage, 0, len(req.ExtractOutputs))
for _, output := range req.ExtractOutputs {
outputs = append(outputs, json.RawMessage(output.Payload.Content))
}
content, err := json.Marshal(map[string]any{"outputs": outputs})
if err != nil {
return contracts.MergeResult{}, err
}
return contracts.MergeResult{
Output: contracts.MergeOutput{
LaneID: req.LaneID,
SourceID: req.Source.ID,
Schema: contracts.ResponseSchema{ID: "fake_event", Name: "fake_event", Version: "v1"},
Payload: contracts.RawPayload{
Content: content,
MediaType: "application/json",
},
},
}, nil
}
type walkingSkeletonNormalizer struct{}
func (normalizer walkingSkeletonNormalizer) Key() string {
return DefaultNormalizeModule
}
func (normalizer walkingSkeletonNormalizer) ReferenceSlots() []contracts.ReferenceSlot {
return nil
}
func (normalizer walkingSkeletonNormalizer) Normalize(ctx context.Context, req contracts.NormalizeRequest) (contracts.NormalizeResult, error) {
var response struct {
Call int `json:"call"`
}
if _, err := req.LLMClient.CompleteStructured(ctx, contracts.StructuredCompletionRequest{
StageName: "fake/normalize",
PromptID: "fake.normalize",
PromptVersion: "v1",
}, &response); err != nil {
return contracts.NormalizeResult{}, err
}
return contracts.NormalizeResult{
Output: contracts.NormalizeOutput{
LaneID: req.LaneID,
SourceID: req.MergeOutput.SourceID,
Schema: req.MergeOutput.Schema,
Payload: req.MergeOutput.Payload,
},
}, nil
}
type walkingSkeletonOutput struct{}
func (output walkingSkeletonOutput) Key() string {
return "json"
}
func (output walkingSkeletonOutput) Encode(ctx context.Context, req contracts.OutputRequest) (contracts.OutputResult, error) {
type rawOutput struct {
LaneID string `json:"lane_id"`
NormalizerKey string `json:"normalizer_key"`
SourceID string `json:"source_id"`
Schema contracts.ResponseSchema `json:"schema"`
MediaType string `json:"media_type"`
Content json.RawMessage `json:"content"`
}
rawOutputs := make([]rawOutput, 0, len(req.NormalizeOutputs))
for _, output := range req.NormalizeOutputs {
rawOutputs = append(rawOutputs, rawOutput{
LaneID: output.LaneID,
NormalizerKey: output.NormalizerKey,
SourceID: output.SourceID,
Schema: output.Schema,
MediaType: output.Payload.MediaType,
Content: json.RawMessage(output.Payload.Content),
})
}
encoded, err := json.Marshal(struct {
Manifest artifacts.RunManifest `json:"manifest"`
NormalizeOutputs []rawOutput `json:"normalize_outputs"`
}{
Manifest: artifacts.RunManifest{
PipelineID: req.Manifest.PipelineID,
PipelineDigest: req.Manifest.PipelineDigest,
ArtifactLanes: req.Manifest.ArtifactLanes,
ValidationStatus: req.Manifest.ValidationStatus,
},
NormalizeOutputs: rawOutputs,
})
if err != nil {
return contracts.OutputResult{}, err
}
return contracts.OutputResult{
Files: []contracts.OutputFile{
{Name: "output.json", ContentType: "application/json", Bytes: encoded},
},
}, nil
}
func readTestFixture(t *testing.T, path string) []byte {
t.Helper()
bytes, err := os.ReadFile(path)
if err != nil {
t.Fatalf("read fixture %q: %v", path, err)
}
return bytes
}
func assertStructuralJSONEqual(t *testing.T, gotBytes, wantBytes []byte) {
t.Helper()
var got any
if err := json.Unmarshal(gotBytes, &got); err != nil {
t.Fatalf("unmarshal actual JSON: %v\n%s", err, gotBytes)
}
var want any
if err := json.Unmarshal(wantBytes, &want); err != nil {
t.Fatalf("unmarshal expected JSON: %v\n%s", err, wantBytes)
}
if !reflect.DeepEqual(got, want) {
gotFormatted, _ := json.MarshalIndent(got, "", " ")
wantFormatted, _ := json.MarshalIndent(want, "", " ")
t.Fatalf("actual JSON:\n%s\nwant:\n%s", gotFormatted, wantFormatted)
}
}
func chunkText(units []source.SourceUnit) string {
parts := make([]string, 0, len(units))
for _, unit := range units {
parts = append(parts, unit.Text)
}
return strings.Join(parts, " ")
}
func rawDigest(raw []byte) string {
sum := sha256.Sum256(raw)
return "sha256:" + hex.EncodeToString(sum[:])
}