Canonicalize chunk units before extraction

This commit is contained in:
2026-07-05 13:28:09 +00:00
parent e700df82d8
commit 95218218e2
5 changed files with 173 additions and 13 deletions

View File

@@ -341,6 +341,106 @@ func TestRunAllowsPartialCoverageAndOverlappingChunks(t *testing.T) {
}
}
func TestRunCanonicalizesChunkUnitsBeforeExtraction(t *testing.T) {
modules := defaultRunnerModules()
modules.input.doc = sourceDocumentWithUnitMetadata()
modules.chunker.chunks = []contracts.SourceChunk{
{
ID: "chunk-0",
SourceID: "source-1",
Index: 0,
Units: []source.SourceUnit{
{
ID: "u1",
Kind: "mutated-kind",
Text: "mutated text",
Metadata: map[string]any{
"speaker": "chunker-speaker",
"note": "chunker note",
},
},
},
},
}
output, err := New(newRunnerRegistries(t, modules)).Run(context.Background(), RunInput{Pipeline: resolvedPipeline()})
if err != nil {
t.Fatalf("Run() error = %v, want nil", err)
}
if len(output.Approved) != 1 {
t.Fatalf("len(Approved) = %d, want 1", len(output.Approved))
}
extractor := modules.extractors["extract-alpha"]
if len(extractor.requests) != 1 {
t.Fatalf("len(extractor requests) = %d, want 1", len(extractor.requests))
}
chunk := extractor.requests[0].Chunk
if chunk == nil {
t.Fatal("extractor chunk = nil, want canonical chunk")
}
if chunk.Units[0].ID != "u1" || chunk.Units[0].Kind != "source-kind" || chunk.Units[0].Text != "source text" {
t.Fatalf("chunk unit = %#v, want source document unit values", chunk.Units[0])
}
if got := chunk.Units[0].Metadata["speaker"]; got != "source-speaker" {
t.Fatalf("chunk unit metadata = %#v, want source document metadata", chunk.Units[0].Metadata)
}
if got := chunk.Units[0].Metadata["topic"]; got != "source-topic" {
t.Fatalf("chunk unit metadata = %#v, want cloned source document metadata", chunk.Units[0].Metadata)
}
modules.input.doc.Units[0].Kind = "changed-kind"
modules.input.doc.Units[0].Text = "changed text"
modules.input.doc.Units[0].Metadata["speaker"] = "changed-speaker"
if chunk.Units[0].Kind != "source-kind" || chunk.Units[0].Text != "source text" || chunk.Units[0].Metadata["speaker"] != "source-speaker" {
t.Fatalf("chunk unit changed after source mutation: %#v", chunk.Units[0])
}
}
func TestRunPreservesChunkMetadataDuringCanonicalization(t *testing.T) {
modules := defaultRunnerModules()
modules.chunker.chunks = []contracts.SourceChunk{
{
ID: "chunk-0",
SourceID: "source-1",
Index: 0,
Units: []source.SourceUnit{
unitWithID("u1"),
},
Metadata: map[string]any{
"scene_title": "Original scene",
"boundary_note": "Chunker note",
},
},
}
_, err := New(newRunnerRegistries(t, modules)).Run(context.Background(), RunInput{Pipeline: resolvedPipeline()})
if err != nil {
t.Fatalf("Run() error = %v, want nil", err)
}
extractor := modules.extractors["extract-alpha"]
if len(extractor.requests) != 1 || extractor.requests[0].Chunk == nil {
t.Fatalf("extractor requests = %#v, want one canonical chunk", extractor.requests)
}
if got := extractor.requests[0].Chunk.Metadata["scene_title"]; got != "Original scene" {
t.Fatalf("chunk metadata = %#v, want chunker metadata", extractor.requests[0].Chunk.Metadata)
}
if got := extractor.requests[0].Chunk.Metadata["boundary_note"]; got != "Chunker note" {
t.Fatalf("chunk metadata = %#v, want chunker metadata", extractor.requests[0].Chunk.Metadata)
}
modules.chunker.chunks[0].Metadata["scene_title"] = "changed"
modules.chunker.chunks[0].Metadata["boundary_note"] = "changed"
if got := extractor.requests[0].Chunk.Metadata["scene_title"]; got != "Original scene" {
t.Fatalf("chunk metadata aliased to chunker map: %#v", extractor.requests[0].Chunk.Metadata)
}
if got := extractor.requests[0].Chunk.Metadata["boundary_note"]; got != "Chunker note" {
t.Fatalf("chunk metadata aliased to chunker map: %#v", extractor.requests[0].Chunk.Metadata)
}
}
func TestRunExecutesChunksAndPassesChunkAndLLMClient(t *testing.T) {
modules := defaultRunnerModules()
llmClient := fakeLLMClient{}
@@ -1334,6 +1434,34 @@ func validSourceDocument() *source.SourceDocument {
}
}
func sourceDocumentWithUnitMetadata() *source.SourceDocument {
return &source.SourceDocument{
ID: "source-1",
Kind: "document",
Format: "text/plain",
Digest: "sha256:source",
Units: []source.SourceUnit{
{
ID: "u1",
Kind: "source-kind",
Text: "source text",
Metadata: map[string]any{
"speaker": "source-speaker",
"topic": "source-topic",
},
},
{
ID: "u2",
Kind: "source-kind",
Text: "second source text",
Metadata: map[string]any{
"speaker": "source-speaker-2",
},
},
},
}
}
func sourceChunkWithID(id string, index int) contracts.SourceChunk {
return contracts.SourceChunk{
ID: id,