Add canonical source unit provenance

This commit is contained in:
2026-07-17 05:19:57 +00:00
parent 15c369c509
commit 40709e4ad8
26 changed files with 254 additions and 34 deletions

View File

@@ -414,6 +414,7 @@ func cloneSourceUnits(units []source.SourceUnit) []source.SourceUnit {
ID: unit.ID,
Kind: unit.Kind,
Text: unit.Text,
Ref: unit.Ref,
Metadata: cloneMetadata(unit.Metadata),
})
}

View File

@@ -22,7 +22,7 @@ func TestWorkspaceRecorderWritesSuccessfulCheckpointFiles(t *testing.T) {
Kind: "document",
Format: "text/plain",
Digest: "sha256:source",
Units: []source.SourceUnit{{ID: 1, Kind: "line", Text: "hello"}},
Units: []source.SourceUnit{{ID: 1, Kind: "line", Text: "hello", Ref: source.SourceRef{SourceID: "source-1", StartUnitID: 1, EndUnitID: 1}}},
}
chunks := []contracts.SourceChunk{
{
@@ -89,7 +89,7 @@ func TestWorkspaceLoaderReusesSuccessfulCheckpointFiles(t *testing.T) {
Kind: "document",
Format: "text/plain",
Digest: "sha256:source",
Units: []source.SourceUnit{{ID: 1, Kind: "line", Text: "hello"}},
Units: []source.SourceUnit{{ID: 1, Kind: "line", Text: "hello", Ref: source.SourceRef{SourceID: "source-1", StartUnitID: 1, EndUnitID: 1}}},
}
chunks := []contracts.SourceChunk{
{
@@ -155,6 +155,9 @@ func TestWorkspaceLoaderReusesSuccessfulCheckpointFiles(t *testing.T) {
if !decision.Reused || sourceCheckpoint.Document.ID != "source-1" {
t.Fatalf("source decision = %#v checkpoint=%#v, want reused", decision, sourceCheckpoint)
}
if got, want := sourceCheckpoint.Document.Units[0].Ref, doc.Units[0].Ref; got != want {
t.Fatalf("checkpoint source unit ref = %#v, want %#v", got, want)
}
chunkCheckpoint, decision := loader.Chunk("generic", doc.Digest)
if !decision.Reused || len(chunkCheckpoint.Chunks) != 1 || string(chunkCheckpoint.Chunks[0].Content) != "chunk content" {
t.Fatalf("chunk decision = %#v checkpoint=%#v, want reused", decision, chunkCheckpoint)