Move chunks into the canonical source model

This commit is contained in:
2026-07-17 05:32:11 +00:00
parent 40709e4ad8
commit 075888c97f
33 changed files with 548 additions and 325 deletions

View File

@@ -135,7 +135,7 @@ func Register(registry *pipeline.ChunkerRegistry) error {
})
}
func chunksFromResponse(doc *source.SourceDocument, response chunkResponse) ([]contracts.SourceChunk, error) {
func chunksFromResponse(doc *source.SourceDocument, response chunkResponse) ([]source.Chunk, error) {
if response.Scenes == nil {
return nil, fmt.Errorf("scenes must be present")
}
@@ -148,7 +148,7 @@ func chunksFromResponse(doc *source.SourceDocument, response chunkResponse) ([]c
unitIndexes[unit.ID] = i
}
chunks := make([]contracts.SourceChunk, 0, len(response.Scenes))
chunks := make([]source.Chunk, 0, len(response.Scenes))
previousEnd := -1
for i, scene := range response.Scenes {
normalized, err := normalizeScene(doc, i, scene)
@@ -186,15 +186,18 @@ func chunksFromResponse(doc *source.SourceDocument, response chunkResponse) ([]c
if err != nil {
return nil, err
}
chunks = append(chunks, contracts.SourceChunk{
ID: fmt.Sprintf("scene-%06d", i+1),
SourceID: doc.ID,
Index: i,
StartUnitID: units[0].ID,
EndUnitID: units[len(units)-1].ID,
Content: content,
MediaType: "application/json",
Units: units,
chunks = append(chunks, source.Chunk{
ID: fmt.Sprintf("scene-%06d", i+1),
SourceID: doc.ID,
Index: i,
Ref: source.SourceRef{
SourceID: doc.ID,
StartUnitID: units[0].Ref.StartUnitID,
EndUnitID: units[len(units)-1].Ref.EndUnitID,
},
Content: content,
MediaType: "application/json",
Units: units,
Metadata: map[string]any{
"scene_title": normalized.ShortTitle,
"primary_mode": normalized.PrimaryMode,

View File

@@ -179,8 +179,8 @@ func TestChunkReturnsSceneChunksFromStructuredOutput(t *testing.T) {
if first.SourceID != "session-alpha" || first.Index != 0 {
t.Fatalf("first chunk = %#v, want source and index fields", first)
}
if first.StartUnitID != 1 || first.EndUnitID != 2 {
t.Fatalf("first boundaries = %d-%d, want 1-2", first.StartUnitID, first.EndUnitID)
if first.Ref != (source.SourceRef{SourceID: "session-alpha", StartUnitID: 1, EndUnitID: 2}) {
t.Fatalf("first ref = %#v, want session-alpha:1-2", first.Ref)
}
if first.MediaType != "application/json" || len(first.Content) == 0 {
t.Fatalf("first payload = media type %q length %d, want JSON content", first.MediaType, len(first.Content))
@@ -574,7 +574,7 @@ func scene(startUnitID int, endUnitID int) sceneResponse {
}
}
func chunkIDs(chunks []contracts.SourceChunk) []string {
func chunkIDs(chunks []source.Chunk) []string {
ids := make([]string, 0, len(chunks))
for _, chunk := range chunks {
ids = append(ids, chunk.ID)

View File

@@ -7,6 +7,7 @@ import (
"strings"
"testing"
"gitea.maximumdirect.net/eric/notarius/internal/core/source"
"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared"
)
@@ -412,12 +413,12 @@ func spellSourceInput() contracts.LLMInputMaterial {
return contracts.NewLLMInputMaterial("source", "application/json", []byte(spellTranscriptJSON), "sha256:transcript", "file:///session-alpha.json")
}
func spellChunkInput(chunk *contracts.SourceChunk) contracts.LLMInputMaterial {
func spellChunkInput(chunk *source.Chunk) contracts.LLMInputMaterial {
return contracts.NewLLMInputMaterial("source", chunk.MediaType, chunk.Content, "sha256:chunk", "file:///session-alpha.json")
}
func emptyChunkRequest(req contracts.ExtractionRequest) contracts.ExtractionRequest {
req.Chunk = &contracts.SourceChunk{
req.Chunk = &source.Chunk{
ID: req.Chunk.ID,
SourceID: req.Chunk.SourceID,
Index: req.Chunk.Index,

View File

@@ -11,16 +11,19 @@ import (
func promptExtractionRequest() contracts.ExtractionRequest {
doc := promptSourceDocument()
chunk := &contracts.SourceChunk{
ID: "session-alpha:chunk:0",
SourceID: doc.ID,
Index: 0,
StartUnitID: doc.Units[0].ID,
EndUnitID: doc.Units[len(doc.Units)-1].ID,
Content: []byte(`{"units":[1,2]}`),
MediaType: "application/json",
Units: append([]source.SourceUnit(nil), doc.Units...),
Metadata: map[string]any{"ignored": "chunk metadata"},
chunk := &source.Chunk{
ID: "session-alpha:chunk:0",
SourceID: doc.ID,
Index: 0,
Ref: source.SourceRef{
SourceID: doc.ID,
StartUnitID: doc.Units[0].ID,
EndUnitID: doc.Units[len(doc.Units)-1].ID,
},
Content: []byte(`{"units":[1,2]}`),
MediaType: "application/json",
Units: append([]source.SourceUnit(nil), doc.Units...),
Metadata: map[string]any{"ignored": "chunk metadata"},
}
return contracts.ExtractionRequest{
Source: doc,

View File

@@ -61,7 +61,7 @@ func (c *Chunker) Chunk(ctx context.Context, req contracts.ChunkRequest) (contra
}
step := opts.maxUnits - opts.overlapUnits
chunks := make([]contracts.SourceChunk, 0, (len(req.Source.Units)+step-1)/step)
chunks := make([]source.Chunk, 0, (len(req.Source.Units)+step-1)/step)
for start := 0; start < len(req.Source.Units); start += step {
end := start + opts.maxUnits
if end > len(req.Source.Units) {
@@ -72,15 +72,18 @@ func (c *Chunker) Chunk(ctx context.Context, req contracts.ChunkRequest) (contra
if err != nil {
return contracts.ChunkResult{}, err
}
chunks = append(chunks, contracts.SourceChunk{
ID: fmt.Sprintf("chunk-%06d", len(chunks)+1),
SourceID: req.Source.ID,
Index: len(chunks),
StartUnitID: units[0].ID,
EndUnitID: units[len(units)-1].ID,
Content: content,
MediaType: "application/json",
Units: units,
chunks = append(chunks, source.Chunk{
ID: fmt.Sprintf("chunk-%06d", len(chunks)+1),
SourceID: req.Source.ID,
Index: len(chunks),
Ref: source.SourceRef{
SourceID: req.Source.ID,
StartUnitID: units[0].Ref.StartUnitID,
EndUnitID: units[len(units)-1].Ref.EndUnitID,
},
Content: content,
MediaType: "application/json",
Units: units,
Metadata: map[string]any{
"start_unit_id": units[0].ID,
"end_unit_id": units[len(units)-1].ID,

View File

@@ -62,8 +62,8 @@ func TestChunkUsesDefaultsForSingleChunk(t *testing.T) {
if got := unitIDs(chunk.Units); !reflect.DeepEqual(got, []int{1, 2, 3}) {
t.Fatalf("unit IDs = %#v, want all units", got)
}
if chunk.StartUnitID != 1 || chunk.EndUnitID != 3 {
t.Fatalf("chunk boundaries = %d-%d, want 1-3", chunk.StartUnitID, chunk.EndUnitID)
if chunk.Ref != (source.SourceRef{SourceID: "source-1", StartUnitID: 1, EndUnitID: 3}) {
t.Fatalf("chunk ref = %#v, want source-1:1-3", chunk.Ref)
}
if chunk.MediaType != "application/json" || len(chunk.Content) == 0 {
t.Fatalf("chunk payload = media type %q length %d, want JSON content", chunk.MediaType, len(chunk.Content))
@@ -209,7 +209,7 @@ func zeroPad3(value int) string {
return fmt.Sprintf("%03d", value)
}
func chunkIDs(chunks []contracts.SourceChunk) []string {
func chunkIDs(chunks []source.Chunk) []string {
ids := make([]string, 0, len(chunks))
for _, chunk := range chunks {
ids = append(ids, chunk.ID)

View File

@@ -244,16 +244,15 @@ func (dndSpellsChunker) ReferenceSlots() []contracts.ReferenceSlot {
func (dndSpellsChunker) Chunk(ctx context.Context, req contracts.ChunkRequest) (contracts.ChunkResult, error) {
return contracts.ChunkResult{
Chunks: []contracts.SourceChunk{
Chunks: []source.Chunk{
{
ID: req.Source.ID + ":chunk:0",
SourceID: req.Source.ID,
Index: 0,
StartUnitID: req.Source.Units[0].ID,
EndUnitID: req.Source.Units[len(req.Source.Units)-1].ID,
Content: []byte(`{"units":[1,2,3]}`),
MediaType: "application/json",
Units: append([]source.SourceUnit(nil), req.Source.Units...),
ID: req.Source.ID + ":chunk:0",
SourceID: req.Source.ID,
Index: 0,
Ref: source.SourceRef{SourceID: req.Source.ID, StartUnitID: req.Source.Units[0].ID, EndUnitID: req.Source.Units[len(req.Source.Units)-1].ID},
Content: []byte(`{"units":[1,2,3]}`),
MediaType: "application/json",
Units: append([]source.SourceUnit(nil), req.Source.Units...),
},
},
}, nil

View File

@@ -169,16 +169,15 @@ func (runnerSeriatimChunker) ReferenceSlots() []contracts.ReferenceSlot {
func (runnerSeriatimChunker) Chunk(ctx context.Context, req contracts.ChunkRequest) (contracts.ChunkResult, error) {
return contracts.ChunkResult{
Chunks: []contracts.SourceChunk{
Chunks: []source.Chunk{
{
ID: req.Source.ID + ":chunk:0",
SourceID: req.Source.ID,
Index: 0,
StartUnitID: req.Source.Units[0].ID,
EndUnitID: req.Source.Units[len(req.Source.Units)-1].ID,
Content: []byte(`{"units":[1,2]}`),
MediaType: "application/json",
Units: append([]source.SourceUnit(nil), req.Source.Units...),
ID: req.Source.ID + ":chunk:0",
SourceID: req.Source.ID,
Index: 0,
Ref: source.SourceRef{SourceID: req.Source.ID, StartUnitID: req.Source.Units[0].ID, EndUnitID: req.Source.Units[len(req.Source.Units)-1].ID},
Content: []byte(`{"units":[1,2]}`),
MediaType: "application/json",
Units: append([]source.SourceUnit(nil), req.Source.Units...),
},
},
}, nil