Record chunking metadata in process runs

internal/core/chunking/summary_test.go

@@ -0,0 +1,148 @@
+package chunking
+
+import (
+	"testing"
+
+	"gitea.maximumdirect.net/eric/audita/internal/core/schema"
+)
+
+func TestComputeSummary(t *testing.T) {
+	config := ChunkingConfig{
+		MaxSectionTokens: 100,
+		MinSectionTokens: 10,
+	}
+
+	sections := []Section{
+		{Index: 0, EstimatedTokens: 30, StartSegmentID: 1, EndSegmentID: 2},
+		{Index: 1, EstimatedTokens: 50, StartSegmentID: 3, EndSegmentID: 4},
+		{Index: 2, EstimatedTokens: 20, StartSegmentID: 5, EndSegmentID: 5},
+	}
+
+	summary := ComputeSummary(sections, config)
+
+	if summary.ChunkCount != 3 {
+		t.Errorf("expected chunk_count=3, got %d", summary.ChunkCount)
+	}
+	if summary.MinEstimatedTokens != 20 {
+		t.Errorf("expected min_estimated_tokens=20, got %d", summary.MinEstimatedTokens)
+	}
+	if summary.MaxEstimatedTokens != 50 {
+		t.Errorf("expected max_estimated_tokens=50, got %d", summary.MaxEstimatedTokens)
+	}
+	if summary.TotalEstimatedTokens != 100 {
+		t.Errorf("expected total_estimated_tokens=100, got %d", summary.TotalEstimatedTokens)
+	}
+	if summary.MaxSectionTokens != 100 {
+		t.Errorf("expected max_section_tokens=100, got %d", summary.MaxSectionTokens)
+	}
+	if summary.MinSectionTokens != 10 {
+		t.Errorf("expected min_section_tokens=10, got %d", summary.MinSectionTokens)
+	}
+	if summary.TargetSections != nil {
+		t.Errorf("expected target_sections=nil, got %v", summary.TargetSections)
+	}
+}
+
+func TestComputeSummaryWithTarget(t *testing.T) {
+	target := 5
+	config := ChunkingConfig{
+		MaxSectionTokens: 100,
+		MinSectionTokens: 10,
+		TargetSections:   &target,
+	}
+
+	sections := []Section{
+		{Index: 0, EstimatedTokens: 30, StartSegmentID: 1, EndSegmentID: 2},
+	}
+
+	summary := ComputeSummary(sections, config)
+
+	if summary.TargetSections == nil || *summary.TargetSections != 5 {
+		t.Errorf("expected target_sections=5, got %v", summary.TargetSections)
+	}
+}
+
+func TestComputeSummaryEmptySections(t *testing.T) {
+	config := ChunkingConfig{
+		MaxSectionTokens: 100,
+		MinSectionTokens: 10,
+	}
+
+	sections := []Section{}
+
+	summary := ComputeSummary(sections, config)
+
+	if summary.ChunkCount != 0 {
+		t.Errorf("expected chunk_count=0, got %d", summary.ChunkCount)
+	}
+	if summary.MinEstimatedTokens != 0 {
+		t.Errorf("expected min_estimated_tokens=0 for empty, got %d", summary.MinEstimatedTokens)
+	}
+	if summary.MaxSectionTokens != 100 {
+		t.Errorf("expected max_section_tokens preserved, got %d", summary.MaxSectionTokens)
+	}
+}
+
+func TestComputeDetailedSummary(t *testing.T) {
+	config := ChunkingConfig{
+		MaxSectionTokens: 100,
+		MinSectionTokens: 10,
+	}
+
+	sections := []Section{
+		{
+			Index:           0,
+			EstimatedTokens: 30,
+			StartSegmentID:  1,
+			EndSegmentID:    2,
+			Segments:        make([]schema.Segment, 2), // 2 segments
+		},
+		{
+			Index:           1,
+			EstimatedTokens: 50,
+			StartSegmentID:  3,
+			EndSegmentID:    5,
+			Segments:        make([]schema.Segment, 3), // 3 segments
+		},
+	}
+
+	detailed := ComputeDetailedSummary(sections, config)
+
+	if detailed.ChunkCount != 2 {
+		t.Errorf("expected chunk_count=2, got %d", detailed.ChunkCount)
+	}
+	if len(detailed.Chunks) != 2 {
+		t.Fatalf("expected 2 chunk entries, got %d", len(detailed.Chunks))
+	}
+
+	// Check first chunk
+	if detailed.Chunks[0].Index != 0 {
+		t.Errorf("expected chunk[0].index=0, got %d", detailed.Chunks[0].Index)
+	}
+	if detailed.Chunks[0].StartSegmentID != 1 {
+		t.Errorf("expected chunk[0].start_segment_id=1, got %d", detailed.Chunks[0].StartSegmentID)
+	}
+	if detailed.Chunks[0].EndSegmentID != 2 {
+		t.Errorf("expected chunk[0].end_segment_id=2, got %d", detailed.Chunks[0].EndSegmentID)
+	}
+	if detailed.Chunks[0].EstimatedTokens != 30 {
+		t.Errorf("expected chunk[0].estimated_tokens=30, got %d", detailed.Chunks[0].EstimatedTokens)
+	}
+	if detailed.Chunks[0].SegmentCount != 2 {
+		t.Errorf("expected chunk[0].segment_count=2, got %d", detailed.Chunks[0].SegmentCount)
+	}
+
+	// Check second chunk
+	if detailed.Chunks[1].Index != 1 {
+		t.Errorf("expected chunk[1].index=1, got %d", detailed.Chunks[1].Index)
+	}
+	if detailed.Chunks[1].StartSegmentID != 3 {
+		t.Errorf("expected chunk[1].start_segment_id=3, got %d", detailed.Chunks[1].StartSegmentID)
+	}
+	if detailed.Chunks[1].EndSegmentID != 5 {
+		t.Errorf("expected chunk[1].end_segment_id=5, got %d", detailed.Chunks[1].EndSegmentID)
+	}
+	if detailed.Chunks[1].SegmentCount != 3 {
+		t.Errorf("expected chunk[1].segment_count=3, got %d", detailed.Chunks[1].SegmentCount)
+	}
+}