Deliver references to eligible runtime targets

This commit is contained in:
2026-07-05 16:38:17 +00:00
parent 4cafde2502
commit 22032dfd6d
7 changed files with 104 additions and 38 deletions

View File

@@ -95,6 +95,7 @@ func (r *Runner) Run(ctx context.Context, input RunInput) (RunOutput, error) {
attachModuleManifestMetadata(&output, "chunker", chunker)
chunkResult, err := chunker.Chunk(ctx, contracts.ChunkRequest{
Source: doc,
References: CloneReferenceSet(input.Pipeline.ChunkReferences.ReferenceSet),
LLMClient: input.LLMClient,
LLMProfile: input.Pipeline.Chunk.LLMProfile,
Options: cloneOptions(input.Pipeline.Chunk.Options),
@@ -224,6 +225,7 @@ func (r *Runner) runLane(ctx context.Context, input RunInput, doc *source.Source
Source: doc,
LaneID: lane.ID,
Candidates: mergeResult.Candidates,
References: CloneReferenceSet(lane.NormalizeReferences.ReferenceSet),
LLMClient: input.LLMClient,
LLMProfile: lane.Normalize.LLMProfile,
Options: cloneOptions(lane.Normalize.Options),

View File

@@ -566,24 +566,7 @@ func TestRunPassesModuleBindingConfigToStageRequests(t *testing.T) {
func TestRunPassesLaneReferencesToExtractorRequests(t *testing.T) {
modules := defaultRunnerModules()
pipeline := resolvedPipeline()
pipeline.ArtifactLanes[0].ExtractReferences.ReferenceSet = contracts.ReferenceSet{
Slots: map[string]contracts.ResolvedReferenceSlot{
"roster": {
Slot: contracts.ReferenceSlot{Name: "roster"},
Items: []contracts.ReferenceItem{
{
SlotName: "roster",
MediaType: "text/plain; charset=utf-8",
Content: []byte("reference text"),
Digest: "sha256:test",
Origin: contracts.ReferenceOrigin{Type: "file", URI: "file:///tmp/reference.txt"},
SizeBytes: int64(len("reference text")),
BindingSource: contracts.ReferenceBindingSourceConfig,
},
},
},
},
}
pipeline.ArtifactLanes[0].ExtractReferences.ReferenceSet = testReferenceSet("roster", "reference text")
_, err := New(newRunnerRegistries(t, modules)).Run(context.Background(), RunInput{Pipeline: pipeline})
if err != nil {
@@ -601,6 +584,55 @@ func TestRunPassesLaneReferencesToExtractorRequests(t *testing.T) {
}
}
func TestRunPassesChunkReferencesToChunkerRequest(t *testing.T) {
modules := defaultRunnerModules()
pipeline := resolvedPipeline()
pipeline.ChunkReferences.ReferenceSet = testReferenceSet("scene_guide", "chunk reference text")
_, err := New(newRunnerRegistries(t, modules)).Run(context.Background(), RunInput{Pipeline: pipeline})
if err != nil {
t.Fatalf("Run() error = %v, want nil", err)
}
req := modules.chunker.requests[0]
item := req.References.Slots["scene_guide"].Items[0]
if string(item.Content) != "chunk reference text" {
t.Fatalf("chunk reference content = %q, want chunk reference text", item.Content)
}
item.Content[0] = 'C'
if got := string(pipeline.ChunkReferences.ReferenceSet.Slots["scene_guide"].Items[0].Content); got != "chunk reference text" {
t.Fatalf("runner mutated chunk reference set content = %q", got)
}
}
func TestRunPassesNormalizeReferencesToNormalizerRequest(t *testing.T) {
modules := defaultRunnerModules()
pipeline := resolvedPipeline()
pipeline.ArtifactLanes[0].NormalizeReferences.ReferenceSet = testReferenceSet("normalization_notes", "normalize reference text")
_, err := New(newRunnerRegistries(t, modules)).Run(context.Background(), RunInput{Pipeline: pipeline})
if err != nil {
t.Fatalf("Run() error = %v, want nil", err)
}
req := modules.normalizers["normalize"].requests[0]
item := req.References.Slots["normalization_notes"].Items[0]
if string(item.Content) != "normalize reference text" {
t.Fatalf("normalize reference content = %q, want normalize reference text", item.Content)
}
item.Content[0] = 'N'
if got := string(pipeline.ArtifactLanes[0].NormalizeReferences.ReferenceSet.Slots["normalization_notes"].Items[0].Content); got != "normalize reference text" {
t.Fatalf("runner mutated normalize reference set content = %q", got)
}
}
func TestRunAllowsNilLLMClientWhenModulesDoNotUseIt(t *testing.T) {
_, err := New(newRunnerRegistries(t, defaultRunnerModules())).Run(context.Background(), RunInput{Pipeline: resolvedPipeline()})
if err != nil {
t.Fatalf("Run() error = %v, want nil with nil LLM client when modules do not use it", err)
}
}
func TestRunIncludesInputWarnings(t *testing.T) {
modules := defaultRunnerModules()
warning := contracts.Warning{Scope: "reference", ReasonCode: "empty_reference", Message: "empty reference"}
@@ -1235,6 +1267,27 @@ func resolvedPipelineWithValidators(validators ...string) ResolvedPipeline {
return pipeline
}
func testReferenceSet(slotName string, content string) contracts.ReferenceSet {
return contracts.ReferenceSet{
Slots: map[string]contracts.ResolvedReferenceSlot{
slotName: {
Slot: contracts.ReferenceSlot{Name: slotName},
Items: []contracts.ReferenceItem{
{
SlotName: slotName,
MediaType: "text/plain; charset=utf-8",
Content: []byte(content),
Digest: "sha256:test",
Origin: contracts.ReferenceOrigin{Type: "file", URI: "file:///tmp/reference.txt"},
SizeBytes: int64(len(content)),
BindingSource: contracts.ReferenceBindingSourceConfig,
},
},
},
},
}
}
type runnerModules struct {
input *runnerInputAdapter
chunker *runnerChunker

View File

@@ -43,8 +43,8 @@ func TestWalkingSkeletonFixture(t *testing.T) {
t.Fatalf("ContentType = %q, want application/json", output.OutputFiles[0].ContentType)
}
assertStructuralJSONEqual(t, output.OutputFiles[0].Bytes, expectedBytes)
if llmClient.calls != 2 {
t.Fatalf("LLM calls = %d, want chunk count 2", llmClient.calls)
if llmClient.calls != 3 {
t.Fatalf("LLM calls = %d, want extractor calls plus normalizer call", llmClient.calls)
}
}
@@ -345,6 +345,15 @@ func (normalizer walkingSkeletonNormalizer) ReferenceSlots() []contracts.Referen
}
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",
ResponseSchemaName: "fake_normalize",
}, &response); err != nil {
return contracts.NormalizeResult{}, err
}
return contracts.NormalizeResult{Candidates: req.Candidates}, nil
}