Remove legacy raw pipeline contracts

This commit is contained in:
2026-07-17 08:13:08 +00:00
parent 814fcdc6ba
commit adfe3825ee
68 changed files with 823 additions and 7919 deletions

View File

@@ -12,14 +12,13 @@ import (
var _ InputAdapter = fakeAdapter{}
var _ Chunker = fakeChunker{}
var _ LegacyRawExtractor = fakeExtractor{}
var _ LegacyRawMerger = fakeMerger{}
var _ LegacyRawNormalizer = fakeNormalizer{}
var _ LegacyRawValidator = fakeValidator{}
var _ Extractor[fakeArtifact] = fakeExtractor{}
var _ Merger[fakeArtifact] = fakeMerger{}
var _ Normalizer[fakeArtifact] = fakeNormalizer{}
var _ StructuredLLMClient = fakeLLMClient{}
var _ OutputEncoder = fakeOutputEncoder{}
func TestFakeExtractorReturnsRawOutput(t *testing.T) {
func TestFakeExtractorReturnsTypedOutput(t *testing.T) {
extractor := fakeExtractor{
key: "generic-extractor",
}
@@ -33,7 +32,7 @@ func TestFakeExtractorReturnsRawOutput(t *testing.T) {
},
}
result, err := extractor.Extract(context.Background(), ExtractionRequest{Source: doc})
result, err := extractor.Extract(context.Background(), TypedExtractionRequest{Source: doc})
if err != nil {
t.Fatalf("Extract() error = %v, want nil", err)
}
@@ -41,14 +40,8 @@ func TestFakeExtractorReturnsRawOutput(t *testing.T) {
if extractor.Key() != "generic-extractor" {
t.Fatalf("Key() = %q, want generic-extractor", extractor.Key())
}
if result.Output.ExtractorKey != "" {
t.Fatalf("ExtractorKey = %q, want runner-owned empty value", result.Output.ExtractorKey)
}
if result.Output.Schema.Version != "v1" {
t.Fatalf("Schema.Version = %q, want v1", result.Output.Schema.Version)
}
if result.Output.Payload.MediaType != "application/json" || string(result.Output.Payload.Content) != `{"value":"example"}` {
t.Fatalf("payload = %q %s, want JSON raw output", result.Output.Payload.MediaType, result.Output.Payload.Content)
if result.Value.Value != "example" {
t.Fatalf("Value = %q, want example", result.Value.Value)
}
}
@@ -139,7 +132,7 @@ func TestFakeExtractorReceivesChunkAndAmbientContext(t *testing.T) {
Units: []source.SourceUnit{doc.Units[1]},
}
result, err := extractor.Extract(context.Background(), ExtractionRequest{
result, err := extractor.Extract(context.Background(), TypedExtractionRequest{
Source: doc,
Chunk: &chunk,
AmbientContext: map[string]any{"mode": "chunked"},
@@ -147,11 +140,8 @@ func TestFakeExtractorReceivesChunkAndAmbientContext(t *testing.T) {
if err != nil {
t.Fatalf("Extract() error = %v, want nil", err)
}
if result.Output.ChunkID != "" || result.Output.ChunkIndex != 0 {
t.Fatalf("chunk provenance = %q/%d, want runner-owned zero values", result.Output.ChunkID, result.Output.ChunkIndex)
}
if string(result.Output.Payload.Content) != `{"value":"chunked"}` {
t.Fatalf("Payload.Content = %s, want chunked payload", result.Output.Payload.Content)
if result.Value.Value != "chunked" {
t.Fatalf("Value = %q, want chunked", result.Value.Value)
}
}
@@ -320,8 +310,8 @@ func TestLLMInputSetCloneCopiesContent(t *testing.T) {
}
}
func TestResponseSchemaJSONOmitRawSchemaContent(t *testing.T) {
schema := ResponseSchema{
func TestArtifactSchemaJSONOmitsSchemaContent(t *testing.T) {
schema := ArtifactSchema{
ID: "schema-id",
Name: "schema-name",
Version: "v1",
@@ -347,26 +337,14 @@ func TestResponseSchemaJSONOmitRawSchemaContent(t *testing.T) {
}
func TestFakeMergeNormalizeAndOutputContracts(t *testing.T) {
extractOutput := ExtractOutput{
LaneID: "generic-lane",
ExtractorKey: "generic-extractor",
SourceID: "source-1",
ChunkID: "source-1:chunk:0",
ChunkIndex: 0,
Schema: ResponseSchema{ID: "schema-id", Name: "schema-name", Version: "v1"},
Payload: RawPayload{
Content: []byte(`{"value":"example"}`),
MediaType: "application/json",
Metadata: map[string]any{"confidence": 0.75},
},
}
extractOutput := ExtractArtifact[fakeArtifact]{LaneID: "generic-lane", ExtractorKey: "generic-extractor", SourceID: "source-1", ChunkID: "source-1:chunk:0", ChunkIndex: 0, Value: fakeArtifact{Value: "example"}}
merger := fakeMerger{key: "generic-merger"}
normalizer := fakeNormalizer{key: "generic-normalizer"}
encoder := fakeOutputEncoder{key: "generic-output"}
merged, err := merger.Merge(context.Background(), MergeRequest{
merged, err := merger.Merge(context.Background(), TypedMergeRequest[fakeArtifact]{
LaneID: "generic-lane",
ExtractOutputs: []ExtractOutput{extractOutput},
ExtractOutputs: []ExtractArtifact[fakeArtifact]{extractOutput},
})
if err != nil {
t.Fatalf("Merge() error = %v, want nil", err)
@@ -374,13 +352,13 @@ func TestFakeMergeNormalizeAndOutputContracts(t *testing.T) {
if merger.Key() != "generic-merger" {
t.Fatalf("Merger.Key() = %q, want generic-merger", merger.Key())
}
if string(merged.Output.Payload.Content) != `{"value":"example"}` {
t.Fatalf("merged content = %s, want raw extract content", merged.Output.Payload.Content)
if merged.Value.Value != "example" {
t.Fatalf("merged value = %q, want example", merged.Value.Value)
}
normalized, err := normalizer.Normalize(context.Background(), NormalizeRequest{
normalized, err := normalizer.Normalize(context.Background(), TypedNormalizeRequest[fakeArtifact]{
LaneID: "generic-lane",
MergeOutput: merged.Output,
MergeOutput: MergeArtifact[fakeArtifact]{LaneID: "generic-lane", MergerKey: merger.Key(), SourceID: "source-1", Value: merged.Value},
})
if err != nil {
t.Fatalf("Normalize() error = %v, want nil", err)
@@ -388,13 +366,13 @@ func TestFakeMergeNormalizeAndOutputContracts(t *testing.T) {
if normalizer.Key() != "generic-normalizer" {
t.Fatalf("Normalizer.Key() = %q, want generic-normalizer", normalizer.Key())
}
if string(normalized.Output.Payload.Content) != `{"value":"example"}` {
t.Fatalf("normalized content = %s, want raw merge content", normalized.Output.Payload.Content)
if normalized.Value.Value != "example" {
t.Fatalf("normalized value = %q, want example", normalized.Value.Value)
}
encoded, err := encoder.Encode(context.Background(), OutputRequest{
Manifest: artifacts.RunManifest{RunID: "run-1"},
NormalizeOutputs: []SerializedOutput{serializedTestOutput(normalized.Output)},
NormalizeOutputs: []SerializedOutput{{LaneID: "generic-lane", NormalizerKey: normalizer.Key(), SourceID: "source-1", Artifact: SerializedArtifact{Kind: "test/artifact", Schema: ArtifactSchema{ID: "schema-id", Name: "schema-name", Version: "v1"}, MediaType: "application/json", Content: []byte(`{"value":"example"}`)}}},
})
if err != nil {
t.Fatalf("Encode() error = %v, want nil", err)
@@ -413,10 +391,6 @@ func TestFakeMergeNormalizeAndOutputContracts(t *testing.T) {
}
}
func serializedTestOutput(output NormalizeOutput) SerializedOutput {
return SerializedOutput{LaneID: output.LaneID, NormalizerKey: output.NormalizerKey, SourceID: output.SourceID, Artifact: SerializedArtifact{Schema: ArtifactSchema{ID: output.Schema.ID, Name: output.Schema.Name, Version: output.Schema.Version, JSONSchema: append([]byte(nil), output.Schema.JSONSchema...)}, MediaType: output.Payload.MediaType, Content: append([]byte(nil), output.Payload.Content...), Metadata: cloneArtifactMetadata(output.Payload.Metadata)}}
}
func TestOutputFileJSONShapeOmitsBytes(t *testing.T) {
file := OutputFile{
Name: "artifacts/events.json",
@@ -514,6 +488,8 @@ type fakeExtractor struct {
key string
}
type fakeArtifact struct{ Value string }
func (extractor fakeExtractor) Key() string {
return extractor.key
}
@@ -522,21 +498,12 @@ func (extractor fakeExtractor) ReferenceSlots() []ReferenceSlot {
return nil
}
func (extractor fakeExtractor) Extract(ctx context.Context, req ExtractionRequest) (ExtractionResult, error) {
payload := json.RawMessage(`{"value":"example"}`)
func (extractor fakeExtractor) Extract(ctx context.Context, req TypedExtractionRequest) (TypedExtractionResult[fakeArtifact], error) {
value := "example"
if req.AmbientContext["mode"] == "chunked" {
payload = json.RawMessage(`{"value":"chunked"}`)
value = "chunked"
}
return ExtractionResult{
Output: ExtractOutput{
Schema: ResponseSchema{ID: "schema-id", Name: "schema-name", Version: "v1"},
Payload: RawPayload{
Content: append([]byte(nil), payload...),
MediaType: "application/json",
},
},
}, nil
return TypedExtractionResult[fakeArtifact]{Value: fakeArtifact{Value: value}}, nil
}
type fakeMerger struct {
@@ -547,15 +514,8 @@ func (merger fakeMerger) Key() string {
return merger.key
}
func (merger fakeMerger) Merge(ctx context.Context, req MergeRequest) (MergeResult, error) {
output := req.ExtractOutputs[0]
return MergeResult{Output: MergeOutput{
LaneID: req.LaneID,
MergerKey: merger.key,
SourceID: output.SourceID,
Schema: output.Schema,
Payload: cloneTestRawPayload(output.Payload),
}}, nil
func (merger fakeMerger) Merge(ctx context.Context, req TypedMergeRequest[fakeArtifact]) (TypedMergeResult[fakeArtifact], error) {
return TypedMergeResult[fakeArtifact]{Value: req.ExtractOutputs[0].Value}, nil
}
type fakeNormalizer struct {
@@ -570,54 +530,8 @@ func (normalizer fakeNormalizer) ReferenceSlots() []ReferenceSlot {
return nil
}
func (normalizer fakeNormalizer) Normalize(ctx context.Context, req NormalizeRequest) (NormalizeResult, error) {
return NormalizeResult{Output: NormalizeOutput{
LaneID: req.LaneID,
NormalizerKey: normalizer.key,
SourceID: req.MergeOutput.SourceID,
Schema: req.MergeOutput.Schema,
Payload: cloneTestRawPayload(req.MergeOutput.Payload),
}}, nil
}
func cloneTestRawPayload(payload RawPayload) RawPayload {
return RawPayload{
Content: append([]byte(nil), payload.Content...),
MediaType: payload.MediaType,
Metadata: cloneTestMetadata(payload.Metadata),
Warnings: append([]Warning(nil), payload.Warnings...),
}
}
func cloneTestMetadata(metadata map[string]any) map[string]any {
if len(metadata) == 0 {
return nil
}
out := make(map[string]any, len(metadata))
for key, value := range metadata {
out[key] = value
}
return out
}
type fakeValidator struct {
name string
}
func (validator fakeValidator) Name() string {
return validator.name
}
func (validator fakeValidator) ExecutionClass() ExecutionClass {
return ExecutionClassDeterministic
}
func (validator fakeValidator) Validate(ctx context.Context, req ValidationRequest) (ValidationResult, error) {
return ValidationResult{
Approved: true,
ReasonCode: "accepted",
Message: "output accepted",
}, nil
func (normalizer fakeNormalizer) Normalize(ctx context.Context, req TypedNormalizeRequest[fakeArtifact]) (TypedNormalizeResult[fakeArtifact], error) {
return TypedNormalizeResult[fakeArtifact]{Value: req.MergeOutput.Value}, nil
}
type fakeLLMClient struct{}