Compare commits

..
Author SHA1 Message Date
Garry TanandClaude Fable 5 d98e6b507f test(config): use withEnv() for TTL env mutation to satisfy check-test-isolation R1
CI verify failed: test/postgres-engine-config-cache.test.ts mutated
process.env.GBRAIN_CONFIG_CACHE_TTL_MS directly in beforeEach/afterEach.
Wrap each test body in withEnv() (test/helpers/with-env.ts) instead.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-22 10:58:53 -07:00
d4bbf6eeae perf(config): batch + cache engine.getConfig to kill ~85 round-trips per query
Takeover of #1694: a single search fires ~85 serial getConfig() reads
(loadConfigWithEngine x2 plus the mode/cache/intent/rerank/graph-signals
resolvers); on a remote pooler each read is a round-trip, dominating query
latency and risking cli.ts's 10s disconnect force-exit truncating stdout.

The first read now batch-loads the whole config table into a process-
lifetime Map (single-flight under concurrency); setConfig/unsetConfig
write through; a 30s TTL bounds multi-writer staleness and
GBRAIN_CONFIG_CACHE_TTL_MS=0 restores per-key reads.

Rebased onto current master: unlike the original diff, both the batch
load and the TTL=0 per-key fallback stay inside connRetry() so the
#1603/#1891 retry+reconnect posture (pooler-drop self-heal) is preserved.
PGLite stays uncached (in-process, zero round-trips; raw-SQL test
fixtures rely on fresh reads). E2E helpers pin the cache off since those
suites seed config via raw SQL.

Co-authored-by: Omerbahari <Omerbahari@users.noreply.github.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-21 14:26:28 -07:00
8 changed files with 186 additions and 112 deletions
+5 -15
View File
@@ -43,7 +43,7 @@ import {
} from '../core/link-extraction.ts';
import { createProgress } from '../core/progress.ts';
import { getCliOptions, cliOptsToProgressOptions } from '../core/cli-options.ts';
import { pathToSlug, slugifyPath, pruneDir, isSyncable } from '../core/sync.ts';
import { pathToSlug, pruneDir, isSyncable } from '../core/sync.ts';
// v0.41.18.0: withRetry + isRetryableConnError + WithRetryOpts moved to
// src/core/retry.ts as the canonical primitive. Engine methods
// (addLinksBatch/addTimelineEntriesBatch/upsertChunks) now self-retry via
@@ -269,24 +269,14 @@ export function extractMarkdownLinks(content: string): { name: string; relTarget
export function resolveSlug(fileDir: string, relTarget: string, allSlugs: Set<string>): string | null {
const targetNoExt = relTarget.endsWith('.md') ? relTarget.slice(0, -3) : relTarget;
// Issue #1964: wikilinks carry raw Obsidian paths (`[[llm-wiki/entities/AI 3.0]]`)
// but allSlugs holds sync-slugified slugs (`llm-wiki/entities/ai-3.0`). Try the
// raw candidate first (back-compat), then the sync-consistent slugified form.
const hit = (candidate: string): string | null => {
if (allSlugs.has(candidate)) return candidate;
const slugified = slugifyPath(candidate);
if (slugified !== candidate && allSlugs.has(slugified)) return slugified;
return null;
};
const s1 = hit(join(fileDir, targetNoExt));
if (s1) return s1;
const s1 = join(fileDir, targetNoExt);
if (allSlugs.has(s1)) return s1;
const parts = fileDir.split('/').filter(Boolean);
for (let strip = 1; strip <= parts.length; strip++) {
const ancestor = parts.slice(0, parts.length - strip).join('/');
const candidate = hit(ancestor ? join(ancestor, targetNoExt) : targetNoExt);
if (candidate) return candidate;
const candidate = ancestor ? join(ancestor, targetNoExt) : targetNoExt;
if (allSlugs.has(candidate)) return candidate;
}
return null;
+4 -20
View File
@@ -14,7 +14,6 @@
import type { BrainEngine } from './engine.ts';
import type { PageType } from './types.ts';
import { ensureWellFormed } from './text-safe.ts';
import { slugifyPath } from './sync.ts';
/**
* v0.42.7 — link-extraction version stamp. Bump this ISO timestamp whenever the
@@ -483,29 +482,14 @@ export async function extractPageLinks(
// pre-v0.40.8.2 behavior of dropping bare wikilinks outside
// DIR_PATTERN.
if (ref.needsResolution) {
if (typeof resolver.resolveBasenameMatches !== 'function') continue;
if (!opts.globalBasename || typeof resolver.resolveBasenameMatches !== 'function') {
continue;
}
// Issue #972 (codex): resolve by the wikilink TARGET (ref.slug — the
// text inside `[[...]]` before any `|`), NOT the display alias
// (ref.name = match[2]). `[[struktura|the project]]` must resolve
// `struktura`, not "the project". The display text is for context only.
//
// Issue #1964: a dir-qualified wikilink (`[[llm-wiki/entities/AI 3.0]]`)
// carries a raw Obsidian path while page slugs are sync-slugified
// (`llm-wiki/entities/ai-3.0`). Slugify the path the same way sync does,
// then match by exact slug or path-suffix (wiki-root-relative authoring).
// This runs regardless of global_basename — it's dir-qualified, so the
// cross-dir false-positive risk the flag guards against doesn't apply.
// Mirrors the FS path's resolveSlug ancestor walk. Bare `[[name]]`
// wikilinks still require the global_basename flag.
let matches: string[] = [];
const slugified = ref.slug.includes('/') ? slugifyPath(ref.slug) : '';
if (slugified.includes('/')) {
const tail = slugified.slice(slugified.lastIndexOf('/') + 1);
matches = (await resolver.resolveBasenameMatches(tail))
.filter(m => m === slugified || m.endsWith(`/${slugified}`));
} else if (opts.globalBasename) {
matches = await resolver.resolveBasenameMatches(ref.slug);
}
const matches = await resolver.resolveBasenameMatches(ref.slug);
if (matches.length === 0) continue;
const idx = content.indexOf(ref.slug);
const context = idx >= 0 ? excerpt(content, idx, 240) : ref.name;
+55 -7
View File
@@ -5565,30 +5565,78 @@ export class PostgresEngine implements BrainEngine {
});
}
/**
* perf (#1694 by @Omerbahari): process-lifetime config cache. A single
* search fires ~85 getConfig() reads (loadConfigWithEngine x2, plus
* mode/cache/intent/rerank/graph-signals resolvers). On a remote pooler
* each read is a round-trip; serial they dominate query latency and can
* push the op handler past cli.ts's 10s disconnect force-exit, truncating
* stdout. First read batch-loads the whole `config` table into this Map
* (inside the same connRetry posture as the per-key read #1603/#1891);
* setConfig/unsetConfig write through. TTL bounds staleness for
* multi-writer processes; GBRAIN_CONFIG_CACHE_TTL_MS=0 disables.
* Only present keys are stored Map.has() distinguishes known-absent.
*/
private _configCache: Map<string, string> | null = null;
private _configCacheLoadedAt = 0;
private _configCacheLoad: Promise<void> | null = null;
private get _configCacheTtlMs(): number {
const raw = process.env.GBRAIN_CONFIG_CACHE_TTL_MS;
if (raw !== undefined) {
const n = parseInt(raw, 10);
if (Number.isFinite(n) && n >= 0) return n;
}
return 30_000;
}
async getConfig(key: string): Promise<string | null> {
// #1603: a transient pooler drop on this read used to throw / fall through
// to defaults silently — which on remote Postgres surfaces as the wrong
// search mode/knobs and empty-stdout queries.
return this.connRetry(async () => {
const rows = await this.sql`SELECT value FROM config WHERE key = ${key}`;
return rows.length > 0 ? (rows[0].value as string) : null;
});
// search mode/knobs and empty-stdout queries. Both the batch load and the
// cache-off per-key read keep the connRetry reconnect posture.
const ttl = this._configCacheTtlMs;
if (ttl === 0) {
return this.connRetry(async () => {
const rows = await this.sql`SELECT value FROM config WHERE key = ${key}`;
return rows.length > 0 ? (rows[0].value as string) : null;
});
}
if (this._configCache === null || Date.now() - this._configCacheLoadedAt >= ttl) {
// Single-flight: concurrent cold reads share one batch load.
this._configCacheLoad ??= this.connRetry(async () => {
const rows = await this.sql`SELECT key, value FROM config` as unknown as
Array<{ key: string; value: string | null }>;
const map = new Map<string, string>();
for (const r of rows) if (r.value != null) map.set(r.key, r.value);
this._configCache = map;
this._configCacheLoadedAt = Date.now();
}).finally(() => {
this._configCacheLoad = null;
});
await this._configCacheLoad;
}
return this._configCache!.has(key) ? this._configCache!.get(key)! : null;
}
async setConfig(key: string, value: string): Promise<void> {
return this.connRetry(async () => {
await this.connRetry(async () => {
await this.sql`
INSERT INTO config (key, value) VALUES (${key}, ${value})
ON CONFLICT (key) DO UPDATE SET value = EXCLUDED.value
`;
});
// Write-through so a long-lived process never serves stale config.
this._configCache?.set(key, value);
}
async unsetConfig(key: string): Promise<number> {
return this.connRetry(async () => {
const count = await this.connRetry(async () => {
const result = await this.sql`DELETE FROM config WHERE key = ${key}` as unknown as { count: number };
return result.count ?? 0;
});
// Write-through: known-absent, so the cache doesn't serve a stale value.
this._configCache?.delete(key);
return count;
}
async listConfigKeys(prefix: string): Promise<string[]> {
+7
View File
@@ -29,6 +29,13 @@ if (existsSync(envPath)) {
}
}
// E2E suites seed/rewrite the config table via raw SQL and expect engine
// reads to see it immediately; disable the process-lifetime config cache
// (#1694) so read semantics match pre-cache behavior. Spawned CLI
// subprocesses inherit this. Cache semantics are pinned by
// test/postgres-engine-config-cache.test.ts.
process.env.GBRAIN_CONFIG_CACHE_TTL_MS ??= '0';
const DATABASE_URL = process.env.DATABASE_URL;
const FIXTURES_DIR = resolve(import.meta.dir, 'fixtures');
-27
View File
@@ -389,33 +389,6 @@ describe('resolveSlugAll', () => {
});
});
// ─── issue #1964: cross-directory wikilinks — slug/path mismatch ──────────
describe('issue #1964: raw Obsidian wikilink paths resolve to sync-slugified slugs', () => {
test('resolveSlug slugifies the candidate (sync-consistent), no flag needed', () => {
const all = new Set(['llm-wiki/entities/ai-3.0']);
// Wikilink literal `[[llm-wiki/entities/AI 3.0]]` — spaces + uppercase.
expect(resolveSlug('llm-wiki/notes', 'llm-wiki/entities/AI 3.0.md', all))
.toBe('llm-wiki/entities/ai-3.0');
});
test('resolveSlug slugifies raw (unslugified) fileDir too', () => {
const all = new Set(['llm-wiki/entities/ai-3.0']);
// fileDir comes from dirname(relPath) — the raw on-disk directory.
expect(resolveSlug('LLM Wiki/Notes', 'entities/AI 3.0.md', all))
.toBe('llm-wiki/entities/ai-3.0');
});
test('extractLinksFromFile resolves cross-directory wikilink with flag OFF as a typed edge', async () => {
const allSlugs = new Set(['llm-wiki/entities/ai-3.0', 'llm-wiki/notes/roadmap']);
const content = '---\ntitle: Roadmap\ntype: concept\n---\n\nSee [[llm-wiki/entities/AI 3.0]].\n';
const links = await extractLinksFromFile(content, 'llm-wiki/notes/roadmap.md', allSlugs);
expect(links.map(l => l.to_slug)).toEqual(['llm-wiki/entities/ai-3.0']);
// Dir-qualified path resolution is exact, NOT the basename fallback.
expect(links[0].link_type).not.toBe('wikilink_basename');
});
});
describe('issue #972 repro: bare wikilinks resolve when flag is on', () => {
// End-to-end: reproduces the issue's exact repro inside a tempdir +
// PGLite, then asserts edge count under both flag states.
-42
View File
@@ -9,8 +9,6 @@ import {
parseTimelineEntries,
isAutoLinkEnabled,
FRONTMATTER_LINK_MAP,
buildBasenameIndex,
queryBasenameIndex,
type SlugResolver,
} from '../src/core/link-extraction.ts';
import type { BrainEngine } from '../src/core/engine.ts';
@@ -426,46 +424,6 @@ describe('extractPageLinks', () => {
expect(strk!.linkType).toBe('wikilink_basename');
});
// ─── issue #1964: dir-qualified wikilinks with raw Obsidian paths ────────
test('#1964: dir-qualified wikilink resolves via sync-consistent slugification (flag OFF)', async () => {
// `[[llm-wiki/entities/AI 3.0]]` is a raw Obsidian path; the page slug
// is the sync-slugified `llm-wiki/entities/ai-3.0`. Must resolve WITHOUT
// global_basename (it's dir-qualified) and must NOT leak to a same-tail
// page in a different directory.
const resolver: SlugResolver = {
resolve: async () => null,
resolveBasenameMatches: async (name) =>
name === 'ai-3.0' ? ['other/ai-3.0', 'llm-wiki/entities/ai-3.0'] : [],
};
const { candidates } = await extractPageLinks(
'llm-wiki/notes/roadmap',
'See [[llm-wiki/entities/AI 3.0]] for the model.',
{}, 'concept', resolver,
// opts.globalBasename omitted (= false) — path is dir-qualified
);
expect(candidates.map(c => c.targetSlug)).toEqual(['llm-wiki/entities/ai-3.0']);
expect(candidates[0].linkType).toBe('wikilink_basename');
expect(candidates[0].linkSource).toBe('wikilink-resolved');
});
test('#1964: path-suffix match resolves wiki-root-relative paths against a real index', async () => {
// Author writes `[[llm-wiki/entities/AI 3.0]]` but the brain nests the
// wiki under a vault dir. Suffix match rescues it; queried through the
// REAL basename index so the tail-key lookup is exercised end to end.
const idx = buildBasenameIndex(['vault/llm-wiki/entities/ai-3.0', 'people/ai-3.0']);
const resolver: SlugResolver = {
resolve: async () => null,
resolveBasenameMatches: async (name) => queryBasenameIndex(idx, name),
};
const { candidates } = await extractPageLinks(
'vault/llm-wiki/notes/roadmap',
'See [[llm-wiki/entities/AI 3.0]].',
{}, 'concept', resolver,
);
expect(candidates.map(c => c.targetSlug)).toEqual(['vault/llm-wiki/entities/ai-3.0']);
});
test('opts.skipFrontmatter suppresses the frontmatter pass', async () => {
// Real resolver shape that WOULD resolve frontmatter source: too,
// but skipFrontmatter blocks the path entirely.
+112
View File
@@ -0,0 +1,112 @@
/**
* Process-lifetime config cache (#1694 takeover, by @Omerbahari).
*
* A single search fires ~85 getConfig() reads; on a remote pooler each is a
* round-trip. The first read now batch-loads the whole `config` table into a
* Map; setConfig/unsetConfig write through; TTL bounds multi-writer
* staleness; GBRAIN_CONFIG_CACHE_TTL_MS=0 restores per-key reads.
*
* Pure: stubs `_sql` with a call-counting fake; no real DB.
*/
import { describe, it, expect } from 'bun:test';
import { PostgresEngine } from '../src/core/postgres-engine.ts';
import { withEnv } from './helpers/with-env.ts';
const FAST_RETRY = { maxRetries: 3, delayMs: 1, delayMaxMs: 1, jitter: 'none' as const };
/** Engine whose `sql` records every query's template strings and returns `rows`. */
function makeEngine(rows: unknown[]) {
const e = new PostgresEngine();
const calls: string[] = [];
(e as unknown as { _connectionStyle: string })._connectionStyle = 'instance';
(e as unknown as { _bulkRetryOptsCache: unknown })._bulkRetryOptsCache = FAST_RETRY;
(e as unknown as { _sql: unknown })._sql = (strings: TemplateStringsArray) => {
calls.push(strings.join('?'));
return Promise.resolve(rows);
};
return { engine: e, calls };
}
/** Run `fn` with GBRAIN_CONFIG_CACHE_TTL_MS set (or cleared when undefined). */
const withTtl = (ttl: string | undefined, fn: () => Promise<void>) =>
withEnv({ GBRAIN_CONFIG_CACHE_TTL_MS: ttl }, fn);
describe('PostgresEngine config cache (#1694)', () => {
it('batch-loads once and serves repeat reads from the cache', () => withTtl(undefined, async () => {
const { engine, calls } = makeEngine([
{ key: 'search.mode', value: 'balanced' },
{ key: 'embedding_multimodal', value: 'true' },
]);
expect(await engine.getConfig('search.mode')).toBe('balanced');
expect(await engine.getConfig('embedding_multimodal')).toBe('true');
expect(await engine.getConfig('search.mode')).toBe('balanced');
// One SELECT total — this is the whole point of the fix.
expect(calls.length).toBe(1);
expect(calls[0]).toContain('SELECT key, value FROM config');
}));
it('returns null for a known-absent key without an extra round-trip', () => withTtl(undefined, async () => {
const { engine, calls } = makeEngine([{ key: 'a', value: '1' }]);
expect(await engine.getConfig('missing.key')).toBeNull();
expect(await engine.getConfig('missing.key')).toBeNull();
expect(calls.length).toBe(1);
}));
it('setConfig writes through so subsequent reads see the new value', () => withTtl(undefined, async () => {
const { engine, calls } = makeEngine([{ key: 'k', value: 'old' }]);
expect(await engine.getConfig('k')).toBe('old');
await engine.setConfig('k', 'new');
expect(await engine.getConfig('k')).toBe('new');
expect(calls.length).toBe(2); // batch load + upsert; no re-read
}));
it('unsetConfig writes through so subsequent reads see absence', () => withTtl(undefined, async () => {
const { engine } = makeEngine([{ key: 'k', value: 'v' }]);
expect(await engine.getConfig('k')).toBe('v');
await engine.unsetConfig('k');
expect(await engine.getConfig('k')).toBeNull();
}));
it('concurrent cold reads share a single batch load (single-flight)', () => withTtl(undefined, async () => {
const { engine, calls } = makeEngine([{ key: 'k', value: 'v' }]);
const [a, b, c] = await Promise.all([
engine.getConfig('k'),
engine.getConfig('k'),
engine.getConfig('other'),
]);
expect([a, b, c]).toEqual(['v', 'v', null]);
expect(calls.length).toBe(1);
}));
it('GBRAIN_CONFIG_CACHE_TTL_MS=0 disables the cache (per-key reads)', () => withTtl('0', async () => {
const { engine, calls } = makeEngine([{ value: 'v' }]);
expect(await engine.getConfig('k')).toBe('v');
expect(await engine.getConfig('k')).toBe('v');
expect(calls.length).toBe(2);
expect(calls[0]).toContain('SELECT value FROM config WHERE key =');
}));
it('an expired TTL reloads from the database', () => withTtl('1', async () => {
const { engine, calls } = makeEngine([{ key: 'k', value: 'v' }]);
expect(await engine.getConfig('k')).toBe('v');
await new Promise((r) => setTimeout(r, 5));
expect(await engine.getConfig('k')).toBe('v');
expect(calls.length).toBe(2); // two batch loads
}));
it('the batch load keeps the connRetry reconnect posture (#1603/#1891)', () => withTtl(undefined, async () => {
const e = new PostgresEngine();
(e as unknown as { _connectionStyle: string })._connectionStyle = 'instance';
(e as unknown as { _sql: unknown })._sql = null; // torn-down pool → retryable
(e as unknown as { _bulkRetryOptsCache: unknown })._bulkRetryOptsCache = FAST_RETRY;
let reconnects = 0;
(e as unknown as { reconnect: () => Promise<void> }).reconnect = async () => {
reconnects++;
(e as unknown as { _sql: unknown })._sql = () =>
Promise.resolve([{ key: 'k', value: 'v' }]);
};
expect(await e.getConfig('k')).toBe('v');
expect(reconnects).toBe(1);
}));
});
@@ -43,7 +43,9 @@ function makeTornDownEngine(poolResult: unknown): { engine: PostgresEngine; reco
describe('PostgresEngine non-batch config accessors self-heal (PR #1891 takeover)', () => {
it('getConfig reconnects + retries a null instance pool, then returns the value', async () => {
const { engine, reconnects } = makeTornDownEngine([{ value: 'live-value' }]);
// Rows carry `key` too: getConfig's default cached path batch-loads
// `SELECT key, value FROM config` (#1694) through the same connRetry.
const { engine, reconnects } = makeTornDownEngine([{ key: 'some.key', value: 'live-value' }]);
expect(await engine.getConfig('some.key')).toBe('live-value');
expect(reconnects()).toBe(1); // exactly one reconnect closed the gap
});