feat(pipeline): feed the current source page into the extraction prompt (#106) (#132)

Co-authored-by: Mathias <mthbqv@gmail.com>

ingestion/internal/pipeline/pipeline_test.go

@@ -277,6 +277,104 @@ func TestRun_ReExtractsWhenTheSourceBodyChanged(t *testing.T) {
 	assert.Equal(t, 2, calls, "changed content must be re-extracted")
 }
 
+// --- #106: page-aware extraction — the model sees the page it is revising --
+
+func TestRun_ExistingSourcePageIsIncludedInTheExtractionPrompt(t *testing.T) {
+	// #103 made the merge asymmetric (on-disk wins); #106 is the other half —
+	// the extraction itself gets to see what's already there instead of
+	// producing a page blind and letting the merge reconcile it afterwards.
+	// This only proves the existing page reaches the prompt; the byte-identical
+	// guarantee for an echoed-back revision is a separate test below.
+	dir := t.TempDir()
+	for _, sub := range []string{"wiki/concepts", "wiki/entities", "wiki/sources"} {
+		require.NoError(t, os.MkdirAll(filepath.Join(dir, sub), 0o755))
+	}
+
+	seeded := "---\ntitle: 'Shape Up'\n---\n\n## Summary\n\nA book about shaping product work.\n\n## Key Claims\n\n- Appetite beats estimation.\n"
+	page := filepath.Join(dir, "wiki", "sources", "shape-up.md")
+	require.NoError(t, os.WriteFile(page, []byte(seeded), 0o644))
+
+	var gotPrompt string
+	cfg := Config{Complete: func(_ context.Context, _, user string) (string, error) {
+		gotPrompt = user
+		return mustJSON([]RawPage{{
+			Title: "Shape Up", Type: "source", Subtype: "book",
+			Content: "## Summary\n\nA book about shaping product work.\n",
+		}}), nil
+	}}
+
+	// Deliberately does not mention "Appetite beats estimation." — that phrase
+	// can only reach the prompt via the existing on-disk page, not the source
+	// content, so its presence proves the page was threaded through.
+	content := "A short editorial update to the book's listing. No new claims here."
+	_, err := Run(context.Background(), cfg, dir, content, "shape-up", false)
+	require.NoError(t, err)
+
+	assert.Contains(t, gotPrompt, "Appetite beats estimation.",
+		"the existing page's content must be visible to the extraction prompt")
+	assert.Contains(t, gotPrompt, "revis", "the prompt must ask for a revision, not a fresh page")
+}
+
+func TestRun_NewSourceHasNoExistingPageInThePrompt(t *testing.T) {
+	// The other side of the same behavior: a source with no page on disk yet
+	// must not get an "existing page" section injected into its prompt at all.
+	dir := t.TempDir()
+	for _, sub := range []string{"wiki/concepts", "wiki/entities", "wiki/sources"} {
+		require.NoError(t, os.MkdirAll(filepath.Join(dir, sub), 0o755))
+	}
+
+	var gotPrompt string
+	cfg := Config{Complete: func(_ context.Context, _, user string) (string, error) {
+		gotPrompt = user
+		return mustJSON([]RawPage{{
+			Title: "New Thing", Type: "source", Subtype: "article",
+			Content: "## Summary\n\nBrand new.\n",
+		}}), nil
+	}}
+
+	_, err := Run(context.Background(), cfg, dir, "Brand new content.", "new-thing", false)
+	require.NoError(t, err)
+
+	assert.NotContains(t, gotPrompt, "Current page",
+		"a source with no page on disk yet must not get a revision section in its prompt")
+}
+
+func TestRun_RevisionEchoingExistingPageStaysByteIdentical(t *testing.T) {
+	// The issue's explicit risk: a model given the current page will sometimes
+	// echo it back verbatim. That must not duplicate content or otherwise
+	// perturb the page — the deterministic merge is still the backstop.
+	dir := t.TempDir()
+	for _, sub := range []string{"wiki/concepts", "wiki/entities", "wiki/sources"} {
+		require.NoError(t, os.MkdirAll(filepath.Join(dir, sub), 0o755))
+	}
+
+	seeded := "---\ntitle: 'Shape Up'\n---\n\n## Summary\n\nA book about shaping product work.\n\n## Key Claims\n\n- Appetite beats estimation.\n"
+	page := filepath.Join(dir, "wiki", "sources", "shape-up.md")
+	require.NoError(t, os.WriteFile(page, []byte(seeded), 0o644))
+
+	cfg := Config{Complete: func(_ context.Context, _, _ string) (string, error) {
+		return mustJSON([]RawPage{{
+			Title: "Shape Up", Type: "source", Subtype: "book",
+			Content: "## Summary\n\nA book about shaping product work.\n\n## Key Claims\n\n- Appetite beats estimation.\n",
+		}}), nil
+	}}
+
+	content := "A short editorial update to the book's listing. No new claims here."
+	result, err := Run(context.Background(), cfg, dir, content, "shape-up", false)
+	require.NoError(t, err)
+	require.False(t, result.Skipped)
+
+	got, err := os.ReadFile(page)
+	require.NoError(t, err)
+
+	want := "---\ntitle: 'Shape Up'\nlast_updated: " + time.Now().UTC().Format("2006-01-02") +
+		"\nsource_hash: " + hashBody(content) + "\n---\n\n" +
+		"## Summary\n\nA book about shaping product work.\n\n" +
+		"## Key Claims\n\n- Appetite beats estimation.\n"
+	assert.Equal(t, want, string(got),
+		"a revision pass that echoes the existing page back must not duplicate or alter its content")
+}
+
 func TestRun_FrontmatterOnlyChangeIsNotDrift(t *testing.T) {
 	// The hash covers the body, so re-fetching a page whose metadata moved
 	// (a re-crawl stamping a new date) is not treated as the source changing.