Compare commits

..
Author SHA1 Message Date
Garry TanandClaude Fable 5 2ba63ddec5 fix(cycle): honor DB-plane config for incremental_extract_include_frontmatter
The gate read loadConfig() (file/env plane) only, but the documented enable
command — gbrain config set autopilot.incremental_extract_include_frontmatter
true — writes the DB plane via engine.setConfig, so the feature could never be
turned on the documented way (silent no-op, #2120 class). Now the file plane
wins when the key is present there; otherwise the DB plane is consulted,
matching the autopilot.auto_drain.* read pattern.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-22 12:16:01 -07:00
214449b190 fix(links): resolve [[wikilink]] + slug-path frontmatter values; keep frontmatter links fresh on the incremental cycle
Takeover/rebase of two community PRs:

PR #1983 — frontmatter link fields never resolved Obsidian-style values:
- makeResolver step 1's strict slug regex rejected digit-leading folders
  (90-people/nicolai) and nested paths (a/b/c); broadened to any slug-shaped
  value with an EXACT getPage match only (no fuzzy, no false positives).
- extractFrontmatterLinks resolved "[[dir/slug]]" verbatim; new anchored
  unwrapWikilink() strips wholly-wrapped [[...]] (and |alias/#heading/^block)
  before resolution. Bare values pass through unchanged.
- Same broadened slug-shape applied to the fs-path synthetic resolver in
  extractLinksFromFile (exact Set membership guards it), so the fs
  frontmatter path resolves PARA-numbered slugs too.

PR #2434 — the cycle's incremental extract (extractForSlugs) extracted body
links only, so externally-edited YAML (sources:/related:) edges drifted
stale. Adds an includeFrontmatter opt (threaded as a param after sourceId,
which master added in #1747/#1503 after the PR was cut), gated by the new
config key autopilot.incremental_extract_include_frontmatter (default off,
preserves body-only behavior).

Tests: unwrapWikilink unit coverage, broadened-resolver + end-to-end
frontmatter cases in test/link-extraction.test.ts; fs-resolver digit-leading
case in test/extract.test.ts; incremental gate off/on cases in
test/extract-incremental.test.ts.

Co-authored-by: spiky02plateau <spiky02plateau@users.noreply.github.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-21 14:23:10 -07:00
12 changed files with 317 additions and 139 deletions
+5 -8
View File
@@ -21,17 +21,14 @@ GBrain is tuned for the Supabase **Transaction pooler** (port 6543): it
auto-disables prepared statements there and routes `engine.transaction()`
(migrations, DDL, sync imports) to a derived **direct** connection
(`db.<ref>.supabase.co:5432`). That direct host is IPv6-only, so on an
IPv4-only host it is unreachable. When that happens gbrain now falls back to
the pooler automatically (one stderr warning, then single-pool mode for the
rest of the process) — but the pooler's ~2-min statement timeout can truncate
very long migrations or bulk imports.
IPv4-only host, reads work but sync **silently skips most pages**. This is the
number one cause of "sync ran but nothing happened."
Fix: make the direct connection reachable over IPv4. Either set
`GBRAIN_DIRECT_DATABASE_URL` to the **Session pooler** string (port 5432 on the
`pooler.supabase.com` host, IPv4), or enable Supabase's IPv4 add-on.
`GBRAIN_DISABLE_DIRECT_POOL=1` skips the direct pool (and the fallback warning)
entirely. Verify by running `gbrain sync` and checking that the page count in
`gbrain stats` matches the syncable file count in the repo.
`pooler.supabase.com` host, IPv4), or enable Supabase's IPv4 add-on. Verify by
running `gbrain sync` and checking that the page count in `gbrain stats` matches
the syncable file count in the repo.
### The Primitives
+5 -8
View File
@@ -2720,17 +2720,14 @@ GBrain is tuned for the Supabase **Transaction pooler** (port 6543): it
auto-disables prepared statements there and routes `engine.transaction()`
(migrations, DDL, sync imports) to a derived **direct** connection
(`db.<ref>.supabase.co:5432`). That direct host is IPv6-only, so on an
IPv4-only host it is unreachable. When that happens gbrain now falls back to
the pooler automatically (one stderr warning, then single-pool mode for the
rest of the process) — but the pooler's ~2-min statement timeout can truncate
very long migrations or bulk imports.
IPv4-only host, reads work but sync **silently skips most pages**. This is the
number one cause of "sync ran but nothing happened."
Fix: make the direct connection reachable over IPv4. Either set
`GBRAIN_DIRECT_DATABASE_URL` to the **Session pooler** string (port 5432 on the
`pooler.supabase.com` host, IPv4), or enable Supabase's IPv4 add-on.
`GBRAIN_DISABLE_DIRECT_POOL=1` skips the direct pool (and the fallback warning)
entirely. Verify by running `gbrain sync` and checking that the page count in
`gbrain stats` matches the syncable file count in the repo.
`pooler.supabase.com` host, IPv4), or enable Supabase's IPv4 add-on. Verify by
running `gbrain sync` and checking that the page count in `gbrain stats` matches
the syncable file count in the repo.
### The Primitives
+22 -3
View File
@@ -433,7 +433,10 @@ export async function extractLinksFromFile(
async resolve(name: string, dirHint?: string | string[]): Promise<string | null> {
if (!name) return null;
const trimmed = name.trim();
if (/^[a-z][a-z0-9-]*\/[a-z0-9][a-z0-9-]*$/.test(trimmed) && allSlugs.has(trimmed)) {
// Same broadened slug-shape as makeResolver step 1: accepts
// digit-leading folders (`90-people/nicolai`) and nested paths.
// Exact Set membership guards it — no false positives.
if (/\//.test(trimmed) && /^[a-z0-9][a-z0-9/_-]*$/.test(trimmed) && allSlugs.has(trimmed)) {
return trimmed;
}
const hints = Array.isArray(dirHint) ? dirHint : (dirHint ? [dirHint] : []);
@@ -582,6 +585,17 @@ export interface ExtractOpts {
* before (single-'default'-source brains unaffected).
*/
sourceId?: string;
/**
* v0.42 — also extract frontmatter links on the incremental (slugs) path.
* `extractForSlugs` extracts BODY links only by default; set this true to also
* parse each changed page's frontmatter so `sources:`/`related:` edges stay fresh
* when YAML is edited externally and synced in. Applied PER changed page, so the
* incremental walk stays bounded (no switch to a full DB scan). Only honored on
* the incremental path (`slugs` defined); the full-walk path already covers
* frontmatter via its own dispatch. Gated upstream by the config key
* `autopilot.incremental_extract_include_frontmatter` (default off).
*/
includeFrontmatter?: boolean;
}
/**
@@ -620,7 +634,7 @@ export async function runExtractCore(engine: BrainEngine, opts: ExtractOpts): Pr
// Nothing changed — skip entirely.
return result;
}
const r = await extractForSlugs(engine, opts.dir, opts.slugs, opts.mode, dryRun, jsonMode, workers, opts.signal, opts.sourceId);
const r = await extractForSlugs(engine, opts.dir, opts.slugs, opts.mode, dryRun, jsonMode, workers, opts.signal, opts.sourceId, opts.includeFrontmatter);
result.links_created = r.links_created;
result.timeline_entries_created = r.timeline_created;
result.pages_processed = r.pages;
@@ -1011,6 +1025,11 @@ async function extractForSlugs(
signal?: AbortSignal,
// #1747/#1503: stamp resolved brain source id on batch rows (see ExtractOpts.sourceId).
sourceId?: string,
// v0.42: when true, also extract frontmatter links per changed page so
// externally-edited YAML (`sources:`/`related:`) stays fresh on the cycle.
// Default false preserves the body-only incremental behavior. Gated upstream
// by `autopilot.incremental_extract_include_frontmatter`.
includeFrontmatter: boolean = false,
): Promise<{ links_created: number; timeline_created: number; pages: number }> {
// Build the full slug set for link resolution (fast: just readdir, no file reads)
const allFiles = walkMarkdownFiles(brainDir);
@@ -1085,7 +1104,7 @@ async function extractForSlugs(
const content = readFileSync(fullPath, 'utf-8');
if (doLinks) {
const links = await extractLinksFromFile(content, relPath, allSlugs, { globalBasename });
const links = await extractLinksFromFile(content, relPath, allSlugs, { globalBasename, includeFrontmatter });
for (const link of links) {
if (dryRun) {
if (!jsonMode) console.log(` ${link.from_slug}${link.to_slug} (${link.link_type})`);
-6
View File
@@ -1078,9 +1078,6 @@ async function initPostgres(opts: {
console.warn(' Direct connections are IPv6 only and fail in many environments.');
console.warn(' Use the Transaction pooler connection string instead (port 6543):');
console.warn(' Supabase Dashboard > Connect (top bar) > Connection String > Transaction pooler');
console.warn(' (With a pooler URL, gbrain derives a direct connection for DDL and falls back');
console.warn(' to the pooler automatically if that host is unreachable. Power users:');
console.warn(' GBRAIN_DIRECT_DATABASE_URL overrides the derived URL; GBRAIN_DISABLE_DIRECT_POOL=1 disables it.)');
console.warn('');
}
@@ -1094,9 +1091,6 @@ async function initPostgres(opts: {
if (databaseUrl.includes('supabase.co') && (msg.includes('ECONNREFUSED') || msg.includes('ETIMEDOUT'))) {
console.error('Connection failed. Supabase direct connections (db.*.supabase.co:5432) are IPv6 only.');
console.error('Use the Transaction pooler connection string instead (port 6543).');
console.error('(gbrain derives its own direct connection from pooler URLs for DDL; if that host is');
console.error('unreachable it falls back to the pooler. GBRAIN_DIRECT_DATABASE_URL overrides the');
console.error('derived URL; GBRAIN_DISABLE_DIRECT_POOL=1 disables the direct pool entirely.)');
}
throw e;
}
+12
View File
@@ -121,6 +121,18 @@ export interface GBrainConfig {
/** Daily spend cap (USD); bounds drains/day = floor(cap / ~$0.30). Default 2.0. */
max_usd_per_day?: number;
};
/**
* v0.42 — keep frontmatter links fresh on the incremental cycle. The cycle's
* extract phase re-extracts only the slugs a sync changed, but `extractForSlugs`
* extracts BODY links only — frontmatter (`sources:`/`related:` etc.) link edges
* silently drift stale when a page's YAML is edited externally and synced in.
* Set true to also extract frontmatter links per changed page each cycle, keeping
* externally-edited YAML edges fresh without a full rescan. Default false
* (preserves current behavior). Read via the file/env/DB plane in the cycle's
* extract dispatch. Disable/enable with
* `gbrain config set autopilot.incremental_extract_include_frontmatter <bool>`.
*/
incremental_extract_include_frontmatter?: boolean;
};
eval?: {
/** false disables capture entirely. Defaults to true. */
+2 -48
View File
@@ -167,25 +167,6 @@ export function deriveDirectUrl(url: string): string | null {
}
}
/**
* Error codes that mean "the direct host is unreachable from this network"
* (#1641). The auto-derived db.<ref>.supabase.co host is IPv6-only without
* the paid IPv4 add-on, so ENOTFOUND/ECONNREFUSED here is expected on
* IPv4-only networks — we fall back to the pooler instead of failing init.
*/
const NETWORK_UNREACHABLE_CODES = [
'ENOTFOUND', 'ECONNREFUSED', 'ENETUNREACH', 'EHOSTUNREACH',
'ETIMEDOUT', 'CONNECT_TIMEOUT',
];
/** True when err looks like a network-unreachable failure (not auth/SQL). */
export function isNetworkUnreachableError(err: unknown): boolean {
const code = (err as { code?: unknown } | null)?.code;
if (typeof code === 'string' && NETWORK_UNREACHABLE_CODES.includes(code)) return true;
const msg = err instanceof Error ? err.message : String(err);
return NETWORK_UNREACHABLE_CODES.some(c => msg.includes(c));
}
/**
* Read kill-switch state from env. Subordinate to parent manager's state
* when present (A2 inheritance).
@@ -338,30 +319,7 @@ export class ConnectionManager {
throw err;
});
}
let pool: Sql | null;
try {
pool = await this._directInit;
} catch (err) {
// #1641: the derived direct host (db.<ref>.supabase.co) is IPv6-only
// without Supabase's IPv4 add-on. On IPv4-only networks the direct
// pool can never connect — permanently fall back to the read pool
// (self-activating kill-switch) instead of failing init/migrations.
// Non-network errors (auth, SQL) still throw: they mean misconfig,
// not unreachability.
if (isNetworkUnreachableError(err)) {
const alreadyWarned = this._killSwitch;
this._killSwitch = true;
const msg = err instanceof Error ? err.message : String(err);
if (!alreadyWarned) console.error(
`gbrain: direct connection to ${this._directUrl ? this.hostOnly(this._directUrl) : 'unknown host'} unreachable (${msg}); ` +
'falling back to the pooler for DDL/bulk (long migrations may hit the pooler statement timeout). ' +
'Set GBRAIN_DIRECT_DATABASE_URL to a reachable direct URL (e.g. the Session pooler, port 5432) or enable the Supabase IPv4 add-on; ' +
'GBRAIN_DISABLE_DIRECT_POOL=1 silences this.',
);
return this.getReadPool();
}
throw err;
}
const pool = await this._directInit;
if (!pool) {
// Defensive — initDirectPool should have thrown.
throw new Error('connection-manager: direct pool init returned null');
@@ -392,9 +350,8 @@ export class ConnectionManager {
},
};
const t0 = Date.now();
let pool: Sql | null = null;
try {
pool = postgres(this._directUrl, opts);
const pool = postgres(this._directUrl, opts);
// Probe to validate connectivity early.
await pool`SELECT 1`;
logConnectionEvent({
@@ -405,9 +362,6 @@ export class ConnectionManager {
});
return pool;
} catch (err) {
// Don't leak the failed pool's sockets/timers (#1641 fallback keeps
// the process running afterward).
if (pool) await endPoolBounded(pool);
logConnectionEvent({
pool: 'ddl',
op: 'error',
+16
View File
@@ -996,6 +996,21 @@ async function runPhaseExtract(
): Promise<PhaseResult> {
try {
const { runExtractCore } = await import('../commands/extract.ts');
const { loadConfig } = await import('./config.ts');
// Default off: the incremental cycle extracts body links only unless the
// operator opts in to keeping externally-edited frontmatter links fresh too.
// Both planes, file wins (env > file > DB precedence, per loadConfigWithEngine):
// `gbrain config set autopilot.incremental_extract_include_frontmatter true`
// writes the DB plane (engine.setConfig), so a file-plane-only read here
// would make the documented enable command a silent no-op (#2120 class).
const fileVal = loadConfig()?.autopilot?.incremental_extract_include_frontmatter;
let includeFrontmatter = fileVal === true;
if (fileVal === undefined) {
try {
includeFrontmatter =
(await engine.getConfig('autopilot.incremental_extract_include_frontmatter')) === 'true';
} catch { /* config table unreadable → default off */ }
}
// Extract is read-mostly against the filesystem + write to links table.
// Honor dryRun by skipping with a 'skipped' entry: extract doesn't have
// a clean dry-run mode today and runCycle should be honest about it.
@@ -1016,6 +1031,7 @@ async function runPhaseExtract(
slugs: changedSlugs, // undefined = full walk (first run / manual)
signal,
sourceId,
includeFrontmatter, // honored on the incremental (slugs) path only
});
const linksCreated = result?.links_created ?? 0;
const timelineCreated = result?.timeline_entries_created ?? 0;
+36 -3
View File
@@ -942,8 +942,17 @@ export function makeResolver(
const hints = Array.isArray(dirHint) ? dirHint : (dirHint ? [dirHint] : []);
// Step 1: already a slug? (dir/name shape, lowercase, hyphenated)
if (/^[a-z][a-z0-9-]*\/[a-z0-9][a-z0-9-]*$/.test(trimmed)) {
// Step 1: already a slug? Try an exact page lookup for any slug-shaped
// value (contains '/', slug charset). Broadened beyond the original
// single-segment lowercase-leading form (`^[a-z][a-z0-9-]*\/[a-z0-9]...`)
// to also accept digit-leading folders (`90-people/nicolai`,
// `01-trading/...`) and nested paths (`a/b/c`) — common in PARA-numbered
// vaults. This is an EXACT getPage match only — no fuzzy — so it never
// produces a false positive; a non-existent slug just falls through to
// the steps below. Fixes frontmatter `related: [[dir/slug]]` values
// (unwrapped by unwrapWikilink) that name a real page the strict regex
// could not reach and whose full-path fuzzy score is below threshold.
if (/\//.test(trimmed) && /^[a-z0-9][a-z0-9/_-]*$/.test(trimmed)) {
const page = await engine.getPage(trimmed);
if (page) {
cache.set(cacheKey, trimmed);
@@ -1003,6 +1012,25 @@ export function makeResolver(
// ─── Frontmatter extractor ──────────────────────────────────────
/**
* Unwrap an Obsidian `[[wikilink]]` frontmatter value to its bare link
* target so the resolver (which expects bare titles / dir slugs) can match
* it. Mainstream Obsidian authors frontmatter links as `related: ["[[Page]]"]`;
* without this, the resolver treats the brackets as part of the value and a
* `[[90-people/nicolai]]` is normalized into `90peoplenicolai`, so it never
* resolves. Strips a trailing `|alias`, `#heading`, or `^block` suffix — the
* link target only. The regex is anchored to a wholly-wrapped value
* (`^\s*\[\[…\]\]\s*$`), so bare titles and any value not fully wrapped pass
* through unchanged and existing behavior is preserved exactly.
*/
export function unwrapWikilink(value: string): string {
const match = /^\s*\[\[(.+?)\]\]\s*$/.exec(value);
if (!match) return value;
// Take the link target: drop |alias, then #heading / ^block suffixes.
const target = match[1].split('|')[0].split('#')[0].split('^')[0];
return target.trim();
}
export interface UnresolvedFrontmatterRef {
/** The frontmatter field name. */
field: string;
@@ -1060,7 +1088,12 @@ export async function extractFrontmatterLinks(
}
if (!name) continue; // skip numbers, nulls, malformed objects
const resolved = await resolver.resolve(name, mapping.dirHint);
// Accept Obsidian `[[wikilink]]` values in frontmatter link fields by
// unwrapping to the bare target before resolution. Bare titles pass
// through unchanged; the original `name` is preserved for the
// unresolved report and edge context.
const linkTarget = unwrapWikilink(name);
const resolved = await resolver.resolve(linkTarget, mapping.dirHint);
if (!resolved) {
unresolved.push({ field, name });
continue;
-63
View File
@@ -3,7 +3,6 @@ import {
isSupabasePoolerUrl,
deriveDirectUrl,
readKillSwitchEnv,
isNetworkUnreachableError,
resolveDirectPoolSize,
ConnectionManager,
DEFAULT_DIRECT_POOL_SIZE,
@@ -239,65 +238,3 @@ describe('ConnectionManager — parent inheritance (A2)', () => {
}
});
});
describe('isNetworkUnreachableError (#1641)', () => {
test('classifies network codes as unreachable', () => {
for (const code of ['ENOTFOUND', 'ECONNREFUSED', 'ENETUNREACH', 'EHOSTUNREACH', 'ETIMEDOUT', 'CONNECT_TIMEOUT']) {
const err = Object.assign(new Error('connect failed'), { code });
expect(isNetworkUnreachableError(err)).toBe(true);
}
});
test('classifies by message when code absent', () => {
expect(isNetworkUnreachableError(new Error('getaddrinfo ENOTFOUND db.abc.supabase.co'))).toBe(true);
});
test('auth/SQL errors are NOT unreachable', () => {
expect(isNetworkUnreachableError(new Error('password authentication failed for user "postgres"'))).toBe(false);
expect(isNetworkUnreachableError(new Error('syntax error at or near "SELEC"'))).toBe(false);
expect(isNetworkUnreachableError(null)).toBe(false);
});
});
describe('ConnectionManager — direct-pool fallback on unreachable host (#1641)', () => {
let originalKillSwitch: string | undefined;
let originalError: typeof console.error;
let errLines: string[];
beforeEach(() => {
originalKillSwitch = process.env.GBRAIN_DISABLE_DIRECT_POOL;
delete process.env.GBRAIN_DISABLE_DIRECT_POOL;
originalError = console.error;
errLines = [];
console.error = (...args: unknown[]) => { errLines.push(args.join(' ')); };
});
afterEach(() => {
console.error = originalError;
if (originalKillSwitch === undefined) delete process.env.GBRAIN_DISABLE_DIRECT_POOL;
else process.env.GBRAIN_DISABLE_DIRECT_POOL = originalKillSwitch;
});
test('ddl() falls back to the read pool when the direct host is unreachable', async () => {
const cm = new ConnectionManager({
url: 'postgresql://postgres.abc:p@aws.pooler.supabase.com:6543/db',
// 127.0.0.1:9 (discard) → instant ECONNREFUSED, the IPv4-only-network shape.
directUrl: 'postgresql://postgres:p@127.0.0.1:9/db',
});
const fakeReadPool = {} as ReturnType<typeof ConnectionManager.prototype.read>;
cm.setReadPool(fakeReadPool);
expect(cm.isDualPoolActive()).toBe(true);
const pool = await cm.ddl(); // without the fix this throws ECONNREFUSED
expect(pool).toBe(fakeReadPool);
// Self-activating kill-switch: subsequent calls skip the direct pool.
expect(cm.isKillSwitchActive()).toBe(true);
expect(cm.isDualPoolActive()).toBe(false);
expect(cm.describeMode().mode).toBe('single (kill-switch)');
// One stderr line mentioning the power-user override.
const warning = errLines.filter(l => l.includes('GBRAIN_DIRECT_DATABASE_URL'));
expect(warning.length).toBe(1);
const again = await cm.ddl();
expect(again).toBe(fakeReadPool);
expect(errLines.filter(l => l.includes('GBRAIN_DIRECT_DATABASE_URL')).length).toBe(1);
}, 20000);
});
+34
View File
@@ -191,3 +191,37 @@ describe('runExtractCore — incremental cycle path (#417)', () => {
expect(result.links_created).toBeGreaterThan(0);
});
});
describe('runExtractCore — incremental frontmatter gate (includeFrontmatter)', () => {
// alice has a `source:` frontmatter edge but NO body links. The incremental
// path extracts body links only by default, so the frontmatter edge is the
// sole signal that distinguishes the gate off vs on.
const aliceFm = '---\nsource: companies/acme-example\n---\n# alice';
test('9. default (flag omitted) does NOT extract frontmatter links on the incremental path', async () => {
await seedPage('companies/acme-example', '# acme');
await seedPage('people/alice-example', aliceFm);
const result = await runExtractCore(engine as unknown as BrainEngine, {
mode: 'all',
dir: tempDir,
slugs: ['people/alice-example'],
});
// alice's only potential edge is her frontmatter `source:`; with the gate off
// it must not be extracted (preserves the body-only incremental behavior).
expect(result.pages_processed).toBe(1);
expect(result.links_created).toBe(0);
});
test('10. includeFrontmatter: true extracts the frontmatter link on the incremental path', async () => {
await seedPage('companies/acme-example', '# acme');
await seedPage('people/alice-example', aliceFm);
const result = await runExtractCore(engine as unknown as BrainEngine, {
mode: 'all',
dir: tempDir,
slugs: ['people/alice-example'],
includeFrontmatter: true,
});
// Same page, gate on → the `source:` frontmatter edge is now extracted.
expect(result.pages_processed).toBe(1);
expect(result.links_created).toBeGreaterThan(0);
});
});
+12
View File
@@ -76,6 +76,18 @@ describe('extractLinksFromFile', () => {
}
});
it('resolves wrapped [[wikilink]] digit-leading slug-path in frontmatter (fs resolver, broadened step 1)', async () => {
// Same bug class as makeResolver step 1 (#1983): the fs resolver's strict
// `^[a-z]…` slug regex rejected digit-leading / nested paths, so a PARA-vault
// `related: "[[90-people/nicolai]]"` never resolved even though the page exists.
const content = '---\nrelated: "[[90-people/nicolai]]"\ntype: concept\n---\nContent.';
const allSlugs = new Set(['wiki/note', '90-people/nicolai']);
const links = await extractLinksFromFile(content, 'wiki/note.md', allSlugs, { includeFrontmatter: true });
const related = links.filter(l => l.link_type === 'related_to');
expect(related).toHaveLength(1);
expect(related[0].to_slug).toBe('90-people/nicolai');
});
it('frontmatter extraction is default OFF (back-compat)', async () => {
// Without includeFrontmatter, fs-source no longer auto-extracts frontmatter.
// Matches db-source behavior. User opts in with --include-frontmatter flag.
+173
View File
@@ -9,6 +9,7 @@ import {
parseTimelineEntries,
isAutoLinkEnabled,
FRONTMATTER_LINK_MAP,
unwrapWikilink,
type SlugResolver,
} from '../src/core/link-extraction.ts';
import type { BrainEngine } from '../src/core/engine.ts';
@@ -1291,3 +1292,175 @@ describe('parseTimelineEntries — Format 3: inline [Source: ..., YYYY-MM-DD] ci
expect(parseTimelineEntries('[Source: import batch, 2025-07-01]')).toHaveLength(0);
});
});
// ─── Frontmatter [[wikilink]] + slug-path resolution ──────────────────────
// Mainstream Obsidian authors frontmatter links as `related: ["[[Page]]"]`,
// and PARA-numbered vaults use digit-leading / nested slug paths like
// `[[90-people/nicolai]]`. Both were silently dropped: brackets were treated
// as part of the value and the step-1 slug regex (`^[a-z]…`) rejected
// digit-leading / nested paths, while full-path fuzzy scored below threshold.
// Fix: unwrapWikilink() before resolution + an exact getPage() for any
// slug-shaped value (exact-match only → no false positives).
describe('unwrapWikilink', () => {
test('wrapped title → bare title', () => {
expect(unwrapWikilink('[[Monday Range]]')).toBe('Monday Range');
});
test('wrapped slug-path (digit-leading folder) → bare slug', () => {
expect(unwrapWikilink('[[90-people/nicolai]]')).toBe('90-people/nicolai');
});
test('wrapped nested slug-path → bare slug', () => {
expect(unwrapWikilink('[[01-trading/wiki/strategies/opening-range-breakout]]'))
.toBe('01-trading/wiki/strategies/opening-range-breakout');
});
test('strips |alias', () => {
expect(unwrapWikilink('[[90-people/nicolai|Nicolai]]')).toBe('90-people/nicolai');
});
test('strips #heading', () => {
expect(unwrapWikilink('[[Page#Section]]')).toBe('Page');
});
test('strips ^block', () => {
expect(unwrapWikilink('[[Page^abc123]]')).toBe('Page');
});
test('surrounding whitespace tolerated', () => {
expect(unwrapWikilink(' [[Page]] ')).toBe('Page');
});
test('bare title passes through unchanged', () => {
expect(unwrapWikilink('Monday Range')).toBe('Monday Range');
});
test('bare slug passes through unchanged', () => {
expect(unwrapWikilink('90-people/nicolai')).toBe('90-people/nicolai');
});
test('partially-wrapped value is NOT unwrapped (anchored)', () => {
// Not a wholly-wrapped value → left intact so existing behavior is exact.
expect(unwrapWikilink('see [[Page]] for detail')).toBe('see [[Page]] for detail');
});
});
describe('makeResolver — slug-path exact getPage (step 1 broadened)', () => {
function fakeEngine(
slugs: string[],
fuzzyMap: Map<string, { slug: string; similarity: number }> = new Map(),
): BrainEngine {
const lookup = new Set(slugs);
return {
async getPage(slug: string) { return lookup.has(slug) ? { slug } as any : null; },
async findByTitleFuzzy(name: string) { return fuzzyMap.get(name) ?? null; },
async searchKeyword() { return []; },
} as unknown as BrainEngine;
}
test('digit-leading folder slug resolves via exact getPage', async () => {
const r = makeResolver(fakeEngine(['90-people/nicolai']));
expect(await r.resolve('90-people/nicolai')).toBe('90-people/nicolai');
});
test('nested (>2 segment) slug resolves via exact getPage', async () => {
const r = makeResolver(fakeEngine(['01-trading/wiki/strategies/opening-range-breakout']));
expect(await r.resolve('01-trading/wiki/strategies/opening-range-breakout'))
.toBe('01-trading/wiki/strategies/opening-range-breakout');
});
test('regression: single-segment lowercase slug still resolves', async () => {
const r = makeResolver(fakeEngine(['people/pedro']));
expect(await r.resolve('people/pedro')).toBe('people/pedro');
});
test('exact-only: slug-shaped value with no matching page falls through (no false positive)', async () => {
// `90-people/ghost` is slug-shaped but absent → step-1 getPage misses,
// no fuzzy hit → null. Never invents an edge.
const r = makeResolver(fakeEngine(['90-people/nicolai']));
expect(await r.resolve('90-people/ghost')).toBeNull();
});
test('non-slug value still routes to fuzzy', async () => {
const r = makeResolver(fakeEngine(
['01-trading/monday-range'],
new Map([['Monday Range', { slug: '01-trading/monday-range', similarity: 1 }]]),
));
expect(await r.resolve('Monday Range')).toBe('01-trading/monday-range');
});
});
describe('extractFrontmatterLinks — [[wikilink]] related: values (end-to-end)', () => {
function fakeEngine(
slugs: string[],
fuzzyMap: Map<string, { slug: string; similarity: number }> = new Map(),
): BrainEngine {
const lookup = new Set(slugs);
return {
async getPage(slug: string) { return lookup.has(slug) ? { slug } as any : null; },
async findByTitleFuzzy(name: string) { return fuzzyMap.get(name) ?? null; },
async searchKeyword() { return []; },
} as unknown as BrainEngine;
}
test('wrapped slug-path related: resolves (the core win)', async () => {
const resolver = makeResolver(fakeEngine(['90-people/nicolai']));
const { candidates, unresolved } = await extractFrontmatterLinks(
'wiki/originals/ideas/note', 'note' as never,
{ related: '[[90-people/nicolai]]' }, resolver,
);
expect(unresolved).toHaveLength(0);
expect(candidates).toHaveLength(1);
expect(candidates[0]).toMatchObject({
fromSlug: 'wiki/originals/ideas/note',
targetSlug: '90-people/nicolai',
linkType: 'related_to',
linkSource: 'frontmatter',
});
});
test('wrapped nested slug-path related: resolves', async () => {
const resolver = makeResolver(fakeEngine(['01-trading/wiki/strategies/opening-range-breakout']));
const { candidates } = await extractFrontmatterLinks(
'wiki/note', 'note' as never,
{ related: ['[[01-trading/wiki/strategies/opening-range-breakout]]'] }, resolver,
);
expect(candidates).toHaveLength(1);
expect(candidates[0].targetSlug).toBe('01-trading/wiki/strategies/opening-range-breakout');
});
test('wrapped value with |alias resolves to the target', async () => {
const resolver = makeResolver(fakeEngine(['90-people/nicolai']));
const { candidates } = await extractFrontmatterLinks(
'wiki/note', 'note' as never,
{ related: '[[90-people/nicolai|Nicolai]]' }, resolver,
);
expect(candidates).toHaveLength(1);
expect(candidates[0].targetSlug).toBe('90-people/nicolai');
});
test('regression: bare slug related: still resolves', async () => {
const resolver = makeResolver(fakeEngine(['90-people/nicolai']));
const { candidates } = await extractFrontmatterLinks(
'wiki/note', 'note' as never,
{ related: '90-people/nicolai' }, resolver,
);
expect(candidates).toHaveLength(1);
expect(candidates[0].targetSlug).toBe('90-people/nicolai');
});
test('regression: wrapped title resolves via fuzzy (brackets harmless)', async () => {
const resolver = makeResolver(fakeEngine(
['01-trading/monday-range'],
new Map([['Monday Range', { slug: '01-trading/monday-range', similarity: 1 }]]),
));
const { candidates } = await extractFrontmatterLinks(
'wiki/note', 'note' as never,
{ related: '[[Monday Range]]' }, resolver,
);
expect(candidates).toHaveLength(1);
expect(candidates[0].targetSlug).toBe('01-trading/monday-range');
});
test('unknown wrapped slug → unresolved (no crash), original value preserved', async () => {
const resolver = makeResolver(fakeEngine(['90-people/nicolai']));
const { candidates, unresolved } = await extractFrontmatterLinks(
'wiki/note', 'note' as never,
{ related: '[[99-archive/does-not-exist]]' }, resolver,
);
expect(candidates).toHaveLength(0);
expect(unresolved).toHaveLength(1);
expect(unresolved[0]).toEqual({ field: 'related', name: '[[99-archive/does-not-exist]]' });
});
});