hyperguild/ingestion/internal/wiki/merge_test.go

// ingestion/internal/wiki/merge_test.go
package wiki

import (
	"strings"
	"testing"

	"github.com/stretchr/testify/assert"
)

func TestMerge_BulletSectionsUnion(t *testing.T) {
	a := Page{Path: "wiki/concepts/foo.md", Content: "---\ntitle: Foo\n---\n\n## Related Concepts\n\n- [[bar|Bar]]\n"}
	b := Page{Path: "wiki/concepts/foo.md", Content: "---\ntitle: Foo\n---\n\n## Related Concepts\n\n- [[bar|Bar]]\n- [[baz|Baz]]\n"}

	got := Merge(a, b)
	assert.Contains(t, got.Content, "[[bar|Bar]]")
	assert.Contains(t, got.Content, "[[baz|Baz]]")
	assert.Equal(t, 1, strings.Count(got.Content, "[[bar|Bar]]"))
}

func TestMerge_AppendSections(t *testing.T) {
	a := Page{Path: "wiki/concepts/foo.md", Content: "---\ntitle: Foo\n---\n\n## Evolving Notes\n\nFirst note.\n"}
	b := Page{Path: "wiki/concepts/foo.md", Content: "---\ntitle: Foo\n---\n\n## Evolving Notes\n\nSecond note.\n"}

	got := Merge(a, b)
	assert.Contains(t, got.Content, "First note.")
	assert.Contains(t, got.Content, "Second note.")
}

func TestMerge_KeepFirstForOtherSections(t *testing.T) {
	a := Page{Path: "wiki/concepts/foo.md", Content: "---\ntitle: Foo\n---\n\n## Definition\n\nFirst definition.\n"}
	b := Page{Path: "wiki/concepts/foo.md", Content: "---\ntitle: Foo\n---\n\n## Definition\n\nSecond definition.\n"}

	got := Merge(a, b)
	assert.Contains(t, got.Content, "First definition.")
	assert.NotContains(t, got.Content, "Second definition.")
}

func TestMerge_NewSectionFromB(t *testing.T) {
	a := Page{Path: "wiki/concepts/foo.md", Content: "---\ntitle: Foo\n---\n\n## Definition\n\nA thing.\n"}
	b := Page{Path: "wiki/concepts/foo.md", Content: "---\ntitle: Foo\n---\n\n## Why It Matters\n\nBecause reasons.\n"}

	got := Merge(a, b)
	assert.Contains(t, got.Content, "A thing.")
	assert.Contains(t, got.Content, "Because reasons.")
}

func TestMerge_KeepsFrontmatterFromA(t *testing.T) {
	a := Page{Path: "p.md", Content: "---\ntitle: A\nlast_updated: 2026-01-01\n---\n\n## Definition\n\nA.\n"}
	b := Page{Path: "p.md", Content: "---\ntitle: B\nlast_updated: 2026-06-01\n---\n\n## Definition\n\nB.\n"}

	got := Merge(a, b)
	assert.Contains(t, got.Content, "title: A")
	assert.NotContains(t, got.Content, "title: B")
}

// --- brain#21/B1: merging must be safe to run again -------------------------

func TestMerge_AppendSectionDoesNotDuplicateContentAlreadyPresent(t *testing.T) {
	// Compile-on-ingest merges a freshly extracted page into the one already
	// on disk. Bullet sections union, so they are naturally idempotent — but
	// append sections concatenate, so re-ingesting an unchanged source would
	// grow "Open Questions" on every run until the page is unreadable.
	page := Page{Path: "wiki/sources/x.md", Content: `---
title: X
---

## Open Questions

- Does this converge?
`}

	once := Merge(page, page)
	twice := Merge(once, page)

	assert.Equal(t, 1, strings.Count(once.Content, "Does this converge?"),
		"merging a page with itself must not duplicate an append section")
	assert.Equal(t, once.Content, twice.Content,
		"merge must be idempotent — a third pass may not keep growing the page")
}

func TestMerge_AppendSectionStillAccumulatesGenuinelyNewContent(t *testing.T) {
	// The dedup must not turn append sections into keep-a-only sections:
	// new material is exactly what compile-on-ingest exists to add.
	existing := Page{Path: "wiki/sources/x.md", Content: `---
title: X
---

## Open Questions

- Does this converge?
`}
	fresh := Page{Path: "wiki/sources/x.md", Content: `---
title: X
---

## Open Questions

- What happens under load?
`}

	got := Merge(existing, fresh).Content
	assert.Contains(t, got, "Does this converge?", "existing question must survive")
	assert.Contains(t, got, "What happens under load?", "new question must be added")
}

func TestMerge_GeneratorOwnedFrontmatterFieldsAreRefreshed(t *testing.T) {
	// #103 made on-disk frontmatter win wholesale, which is what protects
	// human-set fields from a regenerating writer. The cost was that fields the
	// generator legitimately owns — when it last ran, what it last saw — froze
	// at their first-ingest values. An explicit owned-set is the boundary:
	// named fields the generator may refresh, everything else human-owned.
	existing := Page{Path: "wiki/sources/x.md", Content: `---
title: 'X'
last_updated: 2026-01-01
source_hash: aaaa
half_life: durable
claim_provenance: asserted
---

## Summary

Original.
`}
	fresh := Page{Path: "wiki/sources/x.md", Content: `---
title: 'Renamed by the model'
last_updated: 2026-08-22
source_hash: bbbb
---

## Summary

Rewritten by the model.
`}

	got := Merge(existing, fresh).Content

	assert.Contains(t, got, "last_updated: 2026-08-22", "generator owns last_updated")
	assert.Contains(t, got, "source_hash: bbbb", "generator owns source_hash")
	assert.Contains(t, got, "title: 'X'", "a human-set title must survive regeneration")
	assert.Contains(t, got, "half_life: durable", "the claim envelope must survive regeneration")
	assert.Contains(t, got, "claim_provenance: asserted")
	assert.Contains(t, got, "Original.", "an existing section still wins over the model's rewrite")
	assert.NotContains(t, got, "Renamed by the model")
}