* fix(subagent): bind Anthropic SDK messages.create() correctly The makeSubagentHandler was casting `new Anthropic()` directly to MessagesClient, but MessagesClient.create() maps to sdk.messages.create(), not sdk.create(). Every subagent job immediately died with: client.create is not a function Fix: wrap the SDK instance so .create() delegates to .messages.create() with proper `this` binding via .bind(sdk.messages). Discovered on first production run of gbrain agent against Supabase. Co-Authored-By: Wintermute <wintermute@openclaw.ai> * chore(ci): add typescript typecheck to test pipeline + clean up baseline errors Root cause infra gap that let the v0.16.0 subagent bug ship: CI ran only `bun test`, which transpiles types without checking them. Type errors only surfaced at runtime, in production. Changes: - Add `typescript` devDep and a `typecheck` npm script (`tsc --noEmit`). - Chain `bun run typecheck` into `bun run test` so developers get the same pipeline locally that CI runs. - Flip `.github/workflows/test.yml` to invoke `bun run test` (the npm script, including typecheck) instead of `bun test` (runner only). - Clean up 100+ pre-existing type errors across 30+ files so the first run of `tsc --noEmit` is green. Root causes were: - `databaseUrl` → `database_url` rename drift in test fixtures (9 files) - `PageType` union missing `'meeting'` / `'note'` entries that are already used in both src and tests (link-extraction.ts comments acknowledged the gap) - `GBrainConfig.storage` field never declared despite being read in files.ts and operations.ts - `ErrorCode` union missing `'permission_denied'` - `OrchestratorOpts` shape changed; test callers not updated - Dead-code comparisons in migration orchestrators against narrowed status types - postgres.js `Row`-callback type drift on several `.map()` calls - Buffer-as-BodyInit assignment in supabase.ts (real but non-fatal runtime bug; Uint8Array slice works and is type-correct) - Various `as X` single-step casts that now need `as unknown as X` per TS's stricter structural-conversion rules - Bump `beforeAll` hook timeout to 30s on four PGLite-heavy tests that were flaky under parallel test execution: wait-for-completion, extract-fs, e2e/search-quality, e2e/graph-quality. All pass in isolation; timeouts only happened when dozens of PGLite instances init'd simultaneously. The new CI pipeline now fails on any type error across src/ or test/, giving us the compile-time regression guard the subagent fix depends on. * fix(subagent): bind Anthropic SDK messages.create() correctly Shipped bug: v0.16.0 cast `new Anthropic()` to `MessagesClient`, but `.create()` lives at `sdk.messages.create`, not on the top-level client. Every subagent job in production died on first LLM call with `client.create is not a function`. Discovered on the first `gbrain agent run` against Supabase. Fix: assign `sdk.messages` directly to the `MessagesClient` slot. `sdk.messages` IS the object with a callable `.create()`; the original bug was picking the wrong entry point on the SDK. No helper, no wrapper, no `.bind()` — JS method-call semantics preserve `this` at the call site because `subagent.ts:336` invokes `client.create(...)` with `client === sdk.messages`. The one-line assignment also typechecks cleanly against the existing `MessagesClient` interface (SDK's first `create` overload: `(MessageCreateParamsNonStreaming, Core.RequestOptions?) => APIPromise<Message>` is assignable structurally). This gives us compile-time regression protection: anyone reverting to `new Anthropic()` would fail tsc because `Anthropic` has no top-level `.create`. (The companion chore commit puts `tsc --noEmit` in CI so this guard is enforced.) Also adds a `makeAnthropic?: () => Anthropic` dep-injection seam so the factory default construction branch is testable without real API calls. Regression test drives one handler turn through a fake SDK, asserting `sdk.messages.create` is actually called. If someone later reverts to `new Anthropic()`, both guards fire: tsc fails AND the test fails. Co-Authored-By: Wintermute <wintermute@garrytan.com> * chore(tests): add bunfig.toml + 60s hook timeouts to stabilize PGLite-heavy suites After turning on tsc in CI (previous commit), running the full `bun run test` suite in one shot triggered flaky `beforeEach/afterEach hook timed out` failures on 8+ test files. Every failure traced to PGLite WASM init contention when many test files spin up fresh PGLite instances in parallel; each one alone passes in isolation. - `bunfig.toml` sets the global test hook timeout to 60s (default is 5s), covering every test file without per-file edits. - Individual `beforeAll(fn, 60_000)` / `beforeEach(fn, 15_000)` calls on the 8 tests that flaked most stay in place as explicit safety nets so a future bunfig config change doesn't silently re-introduce the flake. Result: 1997 pass, 0 fail on `bun run test` (117 tests added since the prior baseline by picking up typecheck-gated passes). No infrastructure flake tolerated in CI. * chore: bump version and changelog (v0.16.3) Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Wintermute <wintermute@garrytan.com> Co-authored-by: Wintermute <wintermute@openclaw.ai> Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
291 lines
9.7 KiB
TypeScript
291 lines
9.7 KiB
TypeScript
/**
|
|
* gbrain integrity tests — pure regex + frontmatter-extract paths.
|
|
*
|
|
* The three-bucket auto path runs end-to-end in a manual smoke script
|
|
* against a real brain; the unit tests here focus on the pure detection
|
|
* logic (bare-tweet regex, external-link extraction, frontmatter handle
|
|
* extraction) that determines what reaches the resolver.
|
|
*/
|
|
|
|
import { describe, test, expect, beforeAll, afterAll } from 'bun:test';
|
|
import { mkdtempSync, rmSync } from 'fs';
|
|
import { tmpdir } from 'os';
|
|
import { join } from 'path';
|
|
import { PGLiteEngine } from '../src/core/pglite-engine.ts';
|
|
import type { BrainEngine } from '../src/core/engine.ts';
|
|
import {
|
|
findBareTweetHits,
|
|
findExternalLinks,
|
|
extractXHandleFromFrontmatter,
|
|
runIntegrity,
|
|
scanIntegrity,
|
|
} from '../src/commands/integrity.ts';
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// Bare-tweet regex
|
|
// ---------------------------------------------------------------------------
|
|
|
|
describe('findBareTweetHits', () => {
|
|
test('catches "tweeted about X" without URL', () => {
|
|
const hits = findBareTweetHits('Garry tweeted about AI safety last week.', 'people/garrytan');
|
|
expect(hits).toHaveLength(1);
|
|
expect(hits[0].phrase).toMatch(/tweeted about/i);
|
|
expect(hits[0].line).toBe(1);
|
|
});
|
|
|
|
test('catches "in a tweet" style phrasing', () => {
|
|
const compiled = [
|
|
'Some other content.',
|
|
'',
|
|
'He said in a recent tweet that the market was shifting.',
|
|
].join('\n');
|
|
const hits = findBareTweetHits(compiled, 'people/x');
|
|
expect(hits).toHaveLength(1);
|
|
expect(hits[0].line).toBe(3);
|
|
});
|
|
|
|
test('skips line that already has a tweet URL', () => {
|
|
const line = 'As he tweeted about YC (https://x.com/garrytan/status/123456).';
|
|
const hits = findBareTweetHits(line, 'people/x');
|
|
expect(hits).toEqual([]);
|
|
});
|
|
|
|
test('skips fenced code blocks entirely', () => {
|
|
const compiled = [
|
|
'```',
|
|
'He tweeted about the fix.',
|
|
'```',
|
|
].join('\n');
|
|
const hits = findBareTweetHits(compiled, 'people/x');
|
|
expect(hits).toEqual([]);
|
|
});
|
|
|
|
test('detects twitter.com URLs as already-cited too', () => {
|
|
const line = 'She wrote (https://twitter.com/someuser/status/999) about it.';
|
|
const hits = findBareTweetHits(line, 'people/x');
|
|
expect(hits).toEqual([]);
|
|
});
|
|
|
|
test('catches "posted on X"', () => {
|
|
const hits = findBareTweetHits('They posted on X yesterday.', 'people/x');
|
|
expect(hits).toHaveLength(1);
|
|
});
|
|
|
|
test('catches possessive phrasing ("his recent tweet")', () => {
|
|
const hits = findBareTweetHits('His recent tweet said as much.', 'people/x');
|
|
expect(hits).toHaveLength(1);
|
|
});
|
|
|
|
test('does NOT trigger on already-cited "via X/handle" form', () => {
|
|
const hits = findBareTweetHits('Mentioned via X/garrytan earlier.', 'people/x');
|
|
expect(hits).toEqual([]);
|
|
});
|
|
|
|
test('only one hit per line even if multiple phrases match', () => {
|
|
const hits = findBareTweetHits('He tweeted about it in a tweet later.', 'people/x');
|
|
expect(hits).toHaveLength(1);
|
|
});
|
|
});
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// External-link extraction
|
|
// ---------------------------------------------------------------------------
|
|
|
|
describe('findExternalLinks', () => {
|
|
test('extracts http+https URLs', () => {
|
|
const compiled = 'See [the essay](https://example.com/essay) or [legacy](http://old.example/).';
|
|
const hits = findExternalLinks(compiled, 'concepts/x');
|
|
expect(hits.map(h => h.url)).toEqual([
|
|
'https://example.com/essay',
|
|
'http://old.example/',
|
|
]);
|
|
});
|
|
|
|
test('ignores wikilinks without scheme', () => {
|
|
const compiled = 'See [Alice](../people/alice.md) for context.';
|
|
const hits = findExternalLinks(compiled, 'concepts/x');
|
|
expect(hits).toEqual([]);
|
|
});
|
|
|
|
test('ignores links inside fenced code', () => {
|
|
const compiled = '```\n[url](https://example.com)\n```';
|
|
const hits = findExternalLinks(compiled, 'concepts/x');
|
|
expect(hits).toEqual([]);
|
|
});
|
|
|
|
test('line numbers are 1-based and accurate', () => {
|
|
const compiled = 'line 1\n\n[link](https://example.com) on line 3';
|
|
const hits = findExternalLinks(compiled, 'x/y');
|
|
expect(hits[0].line).toBe(3);
|
|
});
|
|
});
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// Frontmatter handle extraction
|
|
// ---------------------------------------------------------------------------
|
|
|
|
describe('extractXHandleFromFrontmatter', () => {
|
|
test('reads x_handle', () => {
|
|
expect(extractXHandleFromFrontmatter({ x_handle: 'garrytan' })).toBe('garrytan');
|
|
});
|
|
|
|
test('reads twitter', () => {
|
|
expect(extractXHandleFromFrontmatter({ twitter: 'garrytan' })).toBe('garrytan');
|
|
});
|
|
|
|
test('reads twitter_handle', () => {
|
|
expect(extractXHandleFromFrontmatter({ twitter_handle: 'garrytan' })).toBe('garrytan');
|
|
});
|
|
|
|
test('strips leading @', () => {
|
|
expect(extractXHandleFromFrontmatter({ x_handle: '@garrytan' })).toBe('garrytan');
|
|
});
|
|
|
|
test('returns null on undefined frontmatter', () => {
|
|
expect(extractXHandleFromFrontmatter(undefined)).toBeNull();
|
|
});
|
|
|
|
test('returns null when no handle key is present', () => {
|
|
expect(extractXHandleFromFrontmatter({ name: 'Garry Tan' })).toBeNull();
|
|
});
|
|
|
|
test('returns null on empty string', () => {
|
|
expect(extractXHandleFromFrontmatter({ x_handle: '' })).toBeNull();
|
|
});
|
|
|
|
test('preference order: x_handle > twitter > twitter_handle > x', () => {
|
|
expect(extractXHandleFromFrontmatter({
|
|
x_handle: 'primary',
|
|
twitter: 'secondary',
|
|
twitter_handle: 'tertiary',
|
|
x: 'quaternary',
|
|
})).toBe('primary');
|
|
});
|
|
});
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// CLI dispatch — non-DB paths (help + review-on-empty)
|
|
// ---------------------------------------------------------------------------
|
|
|
|
// ---------------------------------------------------------------------------
|
|
// scanIntegrity — pure library function called from doctor + cmdCheck
|
|
// ---------------------------------------------------------------------------
|
|
|
|
describe('scanIntegrity', () => {
|
|
let engine: BrainEngine;
|
|
let dbDir: string;
|
|
|
|
beforeAll(async () => {
|
|
dbDir = mkdtempSync(join(tmpdir(), 'scan-integrity-'));
|
|
engine = new PGLiteEngine();
|
|
await engine.connect({ engine: 'pglite', database_path: dbDir });
|
|
await engine.initSchema();
|
|
await engine.putPage('people/alice', {
|
|
type: 'person',
|
|
title: 'Alice',
|
|
compiled_truth: 'Alice tweeted about AI safety last week.',
|
|
timeline: '',
|
|
frontmatter: {},
|
|
});
|
|
await engine.putPage('people/bob', {
|
|
type: 'person',
|
|
title: 'Bob',
|
|
compiled_truth: 'Bob wrote at [example](https://example.com/bob).',
|
|
timeline: '',
|
|
frontmatter: {},
|
|
});
|
|
await engine.putPage('people/legacy', {
|
|
type: 'person',
|
|
title: 'Legacy',
|
|
compiled_truth: 'Legacy tweeted about old stuff.',
|
|
timeline: '',
|
|
frontmatter: { validate: false },
|
|
});
|
|
}, 60_000);
|
|
|
|
afterAll(async () => {
|
|
await engine.disconnect();
|
|
rmSync(dbDir, { recursive: true, force: true });
|
|
});
|
|
|
|
test('counts bare-tweet + external-link hits across pages', async () => {
|
|
const res = await scanIntegrity(engine);
|
|
expect(res.pagesScanned).toBe(2);
|
|
expect(res.bareHits.length).toBe(1);
|
|
expect(res.bareHits[0].slug).toBe('people/alice');
|
|
expect(res.externalHits.length).toBe(1);
|
|
expect(res.externalHits[0].slug).toBe('people/bob');
|
|
});
|
|
|
|
test('skips pages with validate:false frontmatter', async () => {
|
|
const res = await scanIntegrity(engine);
|
|
const slugs = res.bareHits.map(h => h.slug);
|
|
expect(slugs).not.toContain('people/legacy');
|
|
});
|
|
|
|
test('honors limit', async () => {
|
|
const res = await scanIntegrity(engine, { limit: 1 });
|
|
expect(res.pagesScanned).toBe(1);
|
|
});
|
|
|
|
test('honors typeFilter prefix match', async () => {
|
|
const res = await scanIntegrity(engine, { typeFilter: 'companies' });
|
|
expect(res.pagesScanned).toBe(0);
|
|
});
|
|
|
|
test('topPages sorted by hit count', async () => {
|
|
const res = await scanIntegrity(engine);
|
|
expect(res.topPages).toEqual([{ slug: 'people/alice', count: 1 }]);
|
|
});
|
|
});
|
|
|
|
describe('runIntegrity CLI dispatch', () => {
|
|
test('--help prints help without touching engine', async () => {
|
|
const logs: string[] = [];
|
|
const origLog = console.log;
|
|
console.log = (msg?: unknown) => { logs.push(String(msg)); };
|
|
try {
|
|
await runIntegrity(['--help']);
|
|
} finally {
|
|
console.log = origLog;
|
|
}
|
|
expect(logs.join('\n')).toMatch(/gbrain integrity/i);
|
|
});
|
|
|
|
test('no subcommand behaves like --help', async () => {
|
|
const logs: string[] = [];
|
|
const origLog = console.log;
|
|
console.log = (msg?: unknown) => { logs.push(String(msg)); };
|
|
try {
|
|
await runIntegrity([]);
|
|
} finally {
|
|
console.log = origLog;
|
|
}
|
|
expect(logs.join('\n')).toMatch(/integrity/i);
|
|
});
|
|
|
|
test('unknown subcommand prints error + exits', async () => {
|
|
const logs: string[] = [];
|
|
const errs: string[] = [];
|
|
const origLog = console.log;
|
|
const origErr = console.error;
|
|
const origExit = process.exit;
|
|
let exitCode: number | undefined;
|
|
console.log = (msg?: unknown) => { logs.push(String(msg)); };
|
|
console.error = (msg?: unknown) => { errs.push(String(msg)); };
|
|
// prevent process.exit from killing the test runner
|
|
process.exit = ((code?: number) => { exitCode = code; throw new Error('__exit__'); }) as typeof process.exit;
|
|
try {
|
|
await runIntegrity(['nonsense-cmd']);
|
|
} catch (e) {
|
|
if ((e as Error).message !== '__exit__') throw e;
|
|
} finally {
|
|
console.log = origLog;
|
|
console.error = origErr;
|
|
process.exit = origExit;
|
|
}
|
|
expect(exitCode).toBe(1);
|
|
expect(errs.join('\n')).toMatch(/Unknown subcommand/);
|
|
});
|
|
});
|