3084c4173d
classifyByPath had a hole: paths like wiki/index.md or wiki/<slug>.md (direct children of wiki/, no subdirectory) hit the default branch and wrote Wing=parts[1] — which IS the filename, not a wing. Symptom in brain_entities: rows like (slug=index, wing=index.md) and (slug=autobe-..., wing=autobe-evaluation-pattern-....md). Fix: when len(parts) < 3 (no subdirectory at all), fall through to Type=knowledge and let frontmatter set wing/hall if present. Add brain/eval/ artifacts at the same time: - qa-2026-05.md — 20 hand-authored Q→expected-slug pairs covering the homelab knowledge corpus across mcp, dex, gitops, postgres, go, models, methodology - score.py — calls brain_query for each pair, scores top-1 + top-3, emits per-question detail. BRAIN_MCP_TOKEN via env. Pre-fix baseline against the live brain: top-1 = 20% (4/20), top-3 = 65% (13/20). Six hard misses where the expected slug doesn't even land in the top-5. Used to gate the phase 2 DIKW redesign (infra#62 follow-up): if phase 1 fixes (this parser fix + 20 backlink authoring on top orphans) lift top-1 by <10 absolute points, structure is the bottleneck and the tier redesign is justified.
135 lines
3.9 KiB
Go
135 lines
3.9 KiB
Go
package graph
|
|
|
|
import (
|
|
"testing"
|
|
|
|
"github.com/stretchr/testify/assert"
|
|
"github.com/stretchr/testify/require"
|
|
)
|
|
|
|
func TestExtract_HallDoc(t *testing.T) {
|
|
content := []byte(`---
|
|
wing: jepa-fx
|
|
hall: decisions
|
|
title: Val Vol Decision
|
|
---
|
|
# Val Vol
|
|
|
|
See also [[other-decision]] and [[parent-concept|Parent Concept]].
|
|
|
|
Linking to [[unrelated]].
|
|
`)
|
|
|
|
ent, edges, ok := Extract("wiki/jepa-fx/decisions/val-vol.md", content)
|
|
require.True(t, ok)
|
|
assert.Equal(t, "val-vol", ent.Slug)
|
|
assert.Equal(t, "hall", ent.Type)
|
|
assert.Equal(t, "jepa-fx", ent.Wing)
|
|
assert.Equal(t, "decisions", ent.Hall)
|
|
assert.Equal(t, "Val Vol Decision", ent.Title)
|
|
|
|
require.Len(t, edges, 3)
|
|
assert.Equal(t, "other-decision", edges[0].DstSlug)
|
|
assert.Equal(t, "parent-concept", edges[1].DstSlug)
|
|
assert.Equal(t, "unrelated", edges[2].DstSlug)
|
|
for _, e := range edges {
|
|
assert.Equal(t, "wikilink", e.EdgeType)
|
|
assert.Equal(t, "val-vol", e.SrcSlug)
|
|
assert.Equal(t, "wiki/jepa-fx/decisions/val-vol.md", e.SrcDoc)
|
|
assert.Greater(t, e.SrcLine, 0)
|
|
}
|
|
}
|
|
|
|
func TestExtract_LegacyConceptDoc(t *testing.T) {
|
|
content := []byte(`---
|
|
title: Hash Encoding
|
|
---
|
|
# Hash Encoding
|
|
|
|
Linked to [[financial-sentiment-analysis|FSA]].
|
|
`)
|
|
ent, edges, ok := Extract("wiki/concepts/hash-encoding.md", content)
|
|
require.True(t, ok)
|
|
assert.Equal(t, "hash-encoding", ent.Slug)
|
|
assert.Equal(t, "concept", ent.Type)
|
|
assert.Empty(t, ent.Wing)
|
|
assert.Empty(t, ent.Hall)
|
|
assert.Equal(t, "Hash Encoding", ent.Title)
|
|
|
|
require.Len(t, edges, 1)
|
|
assert.Equal(t, "financial-sentiment-analysis", edges[0].DstSlug)
|
|
}
|
|
|
|
func TestExtract_KnowledgeDoc(t *testing.T) {
|
|
content := []byte("# No frontmatter, no links here.\n")
|
|
ent, edges, ok := Extract("knowledge/some-note.md", content)
|
|
require.True(t, ok)
|
|
assert.Equal(t, "some-note", ent.Slug)
|
|
assert.Equal(t, "knowledge", ent.Type)
|
|
assert.Empty(t, edges)
|
|
}
|
|
|
|
func TestExtract_DedupesRepeatedLinkOnSameLine(t *testing.T) {
|
|
content := []byte("See [[foo]] and [[foo]] again on the same line.\n")
|
|
_, edges, ok := Extract("knowledge/dup.md", content)
|
|
require.True(t, ok)
|
|
require.Len(t, edges, 1)
|
|
assert.Equal(t, "foo", edges[0].DstSlug)
|
|
}
|
|
|
|
func TestExtract_KeepsMultipleEdgesOnDifferentLines(t *testing.T) {
|
|
content := []byte("First mention [[foo]].\n\nSecond mention [[foo]].\n")
|
|
_, edges, ok := Extract("knowledge/multi.md", content)
|
|
require.True(t, ok)
|
|
require.Len(t, edges, 2)
|
|
assert.NotEqual(t, edges[0].SrcLine, edges[1].SrcLine)
|
|
}
|
|
|
|
func TestExtract_IgnoresSelfLinks(t *testing.T) {
|
|
content := []byte("Self-reference [[self]] should be ignored.\n")
|
|
_, edges, ok := Extract("knowledge/self.md", content)
|
|
require.True(t, ok)
|
|
assert.Empty(t, edges)
|
|
}
|
|
|
|
func TestExtract_RejectsNonMarkdown(t *testing.T) {
|
|
_, _, ok := Extract("wiki/concepts/not-markdown.txt", []byte("anything"))
|
|
assert.False(t, ok)
|
|
}
|
|
|
|
func TestExtract_LineNumbersAre1Indexed(t *testing.T) {
|
|
content := []byte("line 1\nline 2 [[bar]]\n")
|
|
_, edges, ok := Extract("knowledge/lines.md", content)
|
|
require.True(t, ok)
|
|
require.Len(t, edges, 1)
|
|
assert.Equal(t, 2, edges[0].SrcLine)
|
|
}
|
|
|
|
// Files directly under wiki/ (no subdirectory) used to land
|
|
// Type="hall" Wing="<filename>.md" because the path's second segment
|
|
// was the file itself. The fix routes them to Type="knowledge" with
|
|
// empty Wing/Hall and lets frontmatter set them if present.
|
|
func TestExtract_WikiRootFileIsKnowledgeNotHall(t *testing.T) {
|
|
content := []byte("# Index\n\n- [[foo]]\n")
|
|
ent, _, ok := Extract("wiki/index.md", content)
|
|
require.True(t, ok)
|
|
assert.Equal(t, "index", ent.Slug)
|
|
assert.Equal(t, "knowledge", ent.Type)
|
|
assert.Empty(t, ent.Wing)
|
|
assert.Empty(t, ent.Hall)
|
|
}
|
|
|
|
func TestExtract_WikiRootFileWithFrontmatterWingHall(t *testing.T) {
|
|
content := []byte(`---
|
|
wing: homelab
|
|
hall: facts
|
|
---
|
|
# Some root note
|
|
`)
|
|
ent, _, ok := Extract("wiki/some-note.md", content)
|
|
require.True(t, ok)
|
|
assert.Equal(t, "knowledge", ent.Type)
|
|
assert.Equal(t, "homelab", ent.Wing)
|
|
assert.Equal(t, "facts", ent.Hall)
|
|
}
|