feat(ingestion): add content chunking and LLM JSON output parser

ingestion/internal/pipeline/parse_test.go

@@ -0,0 +1,46 @@
+// ingestion/internal/pipeline/parse_test.go
+package pipeline
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+func TestParsePages_ValidJSON(t *testing.T) {
+	input := `[{"path":"wiki/sources/foo.md","content":"# Foo"},{"path":"wiki/concepts/bar.md","content":"# Bar"}]`
+	pages, warnings := ParsePages(input)
+	require.Len(t, pages, 2)
+	assert.Empty(t, warnings)
+	assert.Equal(t, "wiki/sources/foo.md", pages[0].Path)
+	assert.Equal(t, "wiki/concepts/bar.md", pages[1].Path)
+}
+
+func TestParsePages_StripsFences(t *testing.T) {
+	input := "```json\n[{\"path\":\"wiki/sources/foo.md\",\"content\":\"# Foo\"}]\n```"
+	pages, warnings := ParsePages(input)
+	assert.Len(t, pages, 1)
+	assert.Empty(t, warnings)
+}
+
+func TestParsePages_TruncationRecovery(t *testing.T) {
+	input := `[{"path":"wiki/sources/foo.md","content":"# Foo"},{"path":"wiki/concepts/bar.md","content":"trunc`
+	pages, warnings := ParsePages(input)
+	require.Len(t, pages, 1)
+	assert.Equal(t, "wiki/sources/foo.md", pages[0].Path)
+	assert.NotEmpty(t, warnings)
+}
+
+func TestParsePages_EmptyInput(t *testing.T) {
+	pages, warnings := ParsePages("")
+	assert.Empty(t, pages)
+	assert.NotEmpty(t, warnings)
+}
+
+func TestParsePages_PlainFence(t *testing.T) {
+	input := "```\n[{\"path\":\"wiki/sources/foo.md\",\"content\":\"ok\"}]\n```"
+	pages, warnings := ParsePages(input)
+	assert.Len(t, pages, 1)
+	assert.Empty(t, warnings)
+}