mathiasandClaude Opus 5
6e69698343
AutoTunnel matched note titles case-insensitively, so a one-word title linked
every entry that happened to use that word. Measured on the live corpus: 185
entries carry an auto-written See-also link to wiki/telos/decisions/wrong.md
(title "WRONG") and 136 to .../status.md — the two most-linked nodes in the
whole graph, and both of them artifacts of the English language rather than
references. telos's projects/problems/strategies/goals/beliefs entries account
for another ~60 between them.
That pollution is not cosmetic: inbound-link count is what the duplicate
Fixer picks survivors by, what orphan detection reads, and what brain_graph
shows.
One-word titles now need the title's own casing in the prose ("WRONG", "BERT",
"NLP" — an entity name in a sentence still links). Multi-word titles keep the
case-insensitive match: "risk tier middleware" is a real mention however it is
capitalised, and a three-word collision is not an accident.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
224 lines
8.1 KiB
Go
224 lines
8.1 KiB
Go
package brain_test
|
|
|
|
import (
|
|
"os"
|
|
"path/filepath"
|
|
"strings"
|
|
"testing"
|
|
|
|
"github.com/mathiasbq/hyperguild/ingestion/internal/brain"
|
|
"github.com/stretchr/testify/assert"
|
|
"github.com/stretchr/testify/require"
|
|
)
|
|
|
|
// seedNote writes a minimal markdown note at brainDir/relPath with the given body.
|
|
func seedNote(t *testing.T, brainDir, relPath, body string) {
|
|
t.Helper()
|
|
full := filepath.Join(brainDir, relPath)
|
|
require.NoError(t, os.MkdirAll(filepath.Dir(full), 0o755))
|
|
require.NoError(t, os.WriteFile(full, []byte(body), 0o644))
|
|
}
|
|
|
|
func TestWriteTunnel_AppendsBidirectionalLinks(t *testing.T) {
|
|
dir := t.TempDir()
|
|
seedNote(t, dir, "wiki/jepa-fx/decisions/val-vol.md",
|
|
"---\nwing: jepa-fx\nhall: decisions\n---\n# Val Vol R2\n\nbody.\n")
|
|
seedNote(t, dir, "wiki/hyperguild/decisions/routing.md",
|
|
"---\nwing: hyperguild\nhall: decisions\n---\n# Routing\n\nbody.\n")
|
|
|
|
err := brain.WriteTunnel(dir,
|
|
"wiki/jepa-fx/decisions/val-vol.md",
|
|
"wiki/hyperguild/decisions/routing.md",
|
|
)
|
|
require.NoError(t, err)
|
|
|
|
src, err := os.ReadFile(filepath.Join(dir, "wiki/jepa-fx/decisions/val-vol.md"))
|
|
require.NoError(t, err)
|
|
assert.Contains(t, string(src), "## See also")
|
|
assert.Contains(t, string(src), "[[hyperguild/decisions/routing]]")
|
|
|
|
tgt, err := os.ReadFile(filepath.Join(dir, "wiki/hyperguild/decisions/routing.md"))
|
|
require.NoError(t, err)
|
|
assert.Contains(t, string(tgt), "## See also")
|
|
assert.Contains(t, string(tgt), "[[jepa-fx/decisions/val-vol]]")
|
|
}
|
|
|
|
func TestWriteTunnel_Idempotent(t *testing.T) {
|
|
dir := t.TempDir()
|
|
seedNote(t, dir, "wiki/a/facts/x.md", "# X\n\nbody.\n")
|
|
seedNote(t, dir, "wiki/b/facts/y.md", "# Y\n\nbody.\n")
|
|
|
|
for i := 0; i < 3; i++ {
|
|
require.NoError(t, brain.WriteTunnel(dir,
|
|
"wiki/a/facts/x.md", "wiki/b/facts/y.md"))
|
|
}
|
|
|
|
src, err := os.ReadFile(filepath.Join(dir, "wiki/a/facts/x.md"))
|
|
require.NoError(t, err)
|
|
assert.Equal(t, 1, strings.Count(string(src), "[[b/facts/y]]"),
|
|
"link should appear exactly once after 3 calls")
|
|
assert.Equal(t, 1, strings.Count(string(src), "## See also"))
|
|
|
|
tgt, err := os.ReadFile(filepath.Join(dir, "wiki/b/facts/y.md"))
|
|
require.NoError(t, err)
|
|
assert.Equal(t, 1, strings.Count(string(tgt), "[[a/facts/x]]"))
|
|
assert.Equal(t, 1, strings.Count(string(tgt), "## See also"))
|
|
}
|
|
|
|
func TestWriteTunnel_RejectsSameWing(t *testing.T) {
|
|
dir := t.TempDir()
|
|
seedNote(t, dir, "wiki/jepa-fx/facts/x.md", "x")
|
|
seedNote(t, dir, "wiki/jepa-fx/facts/y.md", "y")
|
|
err := brain.WriteTunnel(dir,
|
|
"wiki/jepa-fx/facts/x.md", "wiki/jepa-fx/facts/y.md")
|
|
require.Error(t, err)
|
|
assert.Contains(t, err.Error(), "cross wings")
|
|
}
|
|
|
|
func TestWriteTunnel_RejectsMissingNote(t *testing.T) {
|
|
dir := t.TempDir()
|
|
seedNote(t, dir, "wiki/a/facts/x.md", "x")
|
|
err := brain.WriteTunnel(dir,
|
|
"wiki/a/facts/x.md", "wiki/b/facts/ghost.md")
|
|
require.Error(t, err)
|
|
}
|
|
|
|
func TestDetectTunnels_ExactTitleMatch(t *testing.T) {
|
|
dir := t.TempDir()
|
|
seedNote(t, dir, "wiki/jepa-fx/decisions/val-vol.md",
|
|
"---\nwing: jepa-fx\nhall: decisions\ntitle: Val Vol R2\n---\nbody.\n")
|
|
seedNote(t, dir, "wiki/jepa-fx/facts/lejpa.md",
|
|
"---\nwing: jepa-fx\nhall: facts\ntitle: LeJPA Architecture\n---\nbody.\n")
|
|
|
|
candidates, err := brain.DetectTunnels(dir,
|
|
"We need to revisit Val Vol R2 in light of new tier data.")
|
|
require.NoError(t, err)
|
|
|
|
require.Len(t, candidates, 1)
|
|
assert.Equal(t, "wiki/jepa-fx/decisions/val-vol.md", candidates[0].TargetPath)
|
|
assert.Equal(t, "Val Vol R2", candidates[0].MatchedTerm)
|
|
assert.True(t, candidates[0].Exact)
|
|
}
|
|
|
|
func TestDetectTunnels_FuzzyMatch(t *testing.T) {
|
|
dir := t.TempDir()
|
|
seedNote(t, dir, "wiki/x/facts/routing-table.md",
|
|
"---\ntitle: 'Routing Table'\n---\nbody.\n")
|
|
|
|
// Substring of title appears in content, but not as a whole word.
|
|
candidates, err := brain.DetectTunnels(dir, "the routing tables were rebuilt")
|
|
require.NoError(t, err)
|
|
require.Len(t, candidates, 1)
|
|
assert.False(t, candidates[0].Exact, "substring-only match should be fuzzy")
|
|
}
|
|
|
|
// A one-word title whose only appearance is lowercase inside another word is
|
|
// not even a candidate: it would fill the review file with English rather than
|
|
// with references.
|
|
func TestDetectTunnels_SingleWordSubstringIsNotACandidate(t *testing.T) {
|
|
dir := t.TempDir()
|
|
seedNote(t, dir, "wiki/x/facts/routing.md",
|
|
"---\ntitle: Routing\n---\nbody.\n")
|
|
|
|
candidates, err := brain.DetectTunnels(dir, "rerouting handles failover")
|
|
require.NoError(t, err)
|
|
assert.Empty(t, candidates)
|
|
}
|
|
|
|
func TestDetectTunnels_NoFrontmatterFallsBackToSlug(t *testing.T) {
|
|
dir := t.TempDir()
|
|
seedNote(t, dir, "wiki/x/facts/widget-flags.md", "# widget flags\n\nbody.\n")
|
|
|
|
candidates, err := brain.DetectTunnels(dir,
|
|
"Documented Widget Flags after the deploy issue.")
|
|
require.NoError(t, err)
|
|
require.Len(t, candidates, 1)
|
|
assert.True(t, candidates[0].Exact)
|
|
assert.Equal(t, "widget flags", candidates[0].MatchedTerm)
|
|
}
|
|
|
|
func TestAutoTunnel_FuzzyGoesToCandidatesFile(t *testing.T) {
|
|
dir := t.TempDir()
|
|
// Existing note in a different wing whose title is "Routing Table".
|
|
seedNote(t, dir, "wiki/other/facts/routing-table.md",
|
|
"---\nwing: other\nhall: facts\ntitle: 'Routing Table'\n---\nbody.\n")
|
|
// Source note in another wing whose body mentions "routing tables"
|
|
// (substring match only — the title is not there as a whole word).
|
|
seedNote(t, dir, "wiki/jepa-fx/facts/new.md",
|
|
"---\nwing: jepa-fx\nhall: facts\n---\nrouting tables rebuilt\n")
|
|
|
|
require.NoError(t, brain.AutoTunnel(dir,
|
|
"wiki/jepa-fx/facts/new.md", "routing tables rebuilt"))
|
|
|
|
// Source must not get auto-linked (fuzzy).
|
|
got, err := os.ReadFile(filepath.Join(dir, "wiki/jepa-fx/facts/new.md"))
|
|
require.NoError(t, err)
|
|
assert.NotContains(t, string(got), "[[other/facts/routing-table]]")
|
|
|
|
// Candidates file must list the pair.
|
|
matches, err := filepath.Glob(filepath.Join(dir, "raw", "tunnel-candidates-*.md"))
|
|
require.NoError(t, err)
|
|
require.Len(t, matches, 1)
|
|
body, err := os.ReadFile(matches[0])
|
|
require.NoError(t, err)
|
|
assert.Contains(t, string(body), "wiki/jepa-fx/facts/new.md")
|
|
assert.Contains(t, string(body), "wiki/other/facts/routing-table.md")
|
|
assert.Contains(t, string(body), "Routing")
|
|
}
|
|
|
|
func TestDetectTunnels_EmptyWiki(t *testing.T) {
|
|
dir := t.TempDir()
|
|
cs, err := brain.DetectTunnels(dir, "anything")
|
|
require.NoError(t, err)
|
|
assert.Empty(t, cs)
|
|
}
|
|
|
|
func TestWriteTunnel_AppendsToExistingSeeAlso(t *testing.T) {
|
|
dir := t.TempDir()
|
|
seedNote(t, dir, "wiki/a/facts/x.md",
|
|
"# X\n\nbody.\n\n## See also\n\n- [[a/facts/old]]\n")
|
|
seedNote(t, dir, "wiki/b/facts/y.md", "# Y\n\nbody.\n")
|
|
|
|
require.NoError(t, brain.WriteTunnel(dir,
|
|
"wiki/a/facts/x.md", "wiki/b/facts/y.md"))
|
|
|
|
src, err := os.ReadFile(filepath.Join(dir, "wiki/a/facts/x.md"))
|
|
require.NoError(t, err)
|
|
s := string(src)
|
|
assert.Equal(t, 1, strings.Count(s, "## See also"), "should reuse existing section")
|
|
assert.Contains(t, s, "[[a/facts/old]]")
|
|
assert.Contains(t, s, "[[b/facts/y]]")
|
|
}
|
|
|
|
// A one-word title matched case-insensitively links every entry that happens
|
|
// to use that word. Live cost before this rule: 185 entries auto-linked to
|
|
// wiki/telos/decisions/wrong.md (title "WRONG") and 136 to .../status.md,
|
|
// making the two most-linked nodes in the graph pure artifacts.
|
|
func TestDetectTunnels_SingleWordTitleNeedsAnExactCaseMatch(t *testing.T) {
|
|
dir := t.TempDir()
|
|
seedNote(t, dir, "wiki/telos/decisions/wrong.md",
|
|
"---\nwing: telos\nhall: decisions\ntitle: WRONG\n---\n# WRONG\n\nRetired beliefs.\n")
|
|
|
|
got, err := brain.DetectTunnels(dir, "The obvious fix was to reject the write. Wrong here.")
|
|
require.NoError(t, err)
|
|
for _, c := range got {
|
|
assert.False(t, c.Exact, "a lowercase prose word must not auto-link a one-word title: %+v", c)
|
|
}
|
|
|
|
got, err = brain.DetectTunnels(dir, "The beliefs listed under WRONG were retired.")
|
|
require.NoError(t, err)
|
|
require.Len(t, got, 1)
|
|
assert.True(t, got[0].Exact, "the title's own casing appearing in prose is a real reference")
|
|
}
|
|
|
|
func TestDetectTunnels_MultiWordTitleStaysCaseInsensitive(t *testing.T) {
|
|
dir := t.TempDir()
|
|
seedNote(t, dir, "wiki/homelab/facts/risk-tier.md",
|
|
"---\nwing: homelab\nhall: facts\ntitle: 'Risk Tier Middleware'\n---\nbody\n")
|
|
|
|
got, err := brain.DetectTunnels(dir, "We rebuilt the risk tier middleware last week.")
|
|
require.NoError(t, err)
|
|
require.Len(t, got, 1)
|
|
assert.True(t, got[0].Exact)
|
|
}
|