mirror of
https://github.com/garrytan/gbrain.git
synced 2026-07-27 22:15:33 +00:00
* 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>
216 lines
7.8 KiB
TypeScript
216 lines
7.8 KiB
TypeScript
/**
|
||
* Quiet-hours + stagger tests — pure primitives + migration verification.
|
||
*
|
||
* Worker-loop integration (claim → release on quiet verdict) is covered by
|
||
* the existing Minions resilience E2E when combined with this unit coverage:
|
||
* the worker path only reads the evaluator result, and the evaluator is
|
||
* exhaustively tested here.
|
||
*/
|
||
|
||
import { describe, test, expect, beforeAll, afterAll } from 'bun:test';
|
||
import { tmpdir } from 'os';
|
||
import { mkdtempSync, rmSync } from 'fs';
|
||
import { join } from 'path';
|
||
|
||
import { PGLiteEngine } from '../src/core/pglite-engine.ts';
|
||
import type { BrainEngine } from '../src/core/engine.ts';
|
||
|
||
import {
|
||
evaluateQuietHours,
|
||
localHour,
|
||
type QuietHoursConfig,
|
||
} from '../src/core/minions/quiet-hours.ts';
|
||
import { staggerMinuteOffset, staggerSecondOffset } from '../src/core/minions/stagger.ts';
|
||
|
||
// ---------------------------------------------------------------------------
|
||
// Pure: evaluateQuietHours
|
||
// ---------------------------------------------------------------------------
|
||
|
||
describe('evaluateQuietHours', () => {
|
||
const tz = 'UTC'; // deterministic across CI
|
||
|
||
test('null config → allow', () => {
|
||
expect(evaluateQuietHours(null)).toBe('allow');
|
||
});
|
||
|
||
test('undefined config → allow', () => {
|
||
expect(evaluateQuietHours(undefined)).toBe('allow');
|
||
});
|
||
|
||
test('invalid config (out-of-range hour) → allow (fail-open)', () => {
|
||
expect(evaluateQuietHours({ start: 99, end: 1, tz })).toBe('allow');
|
||
});
|
||
|
||
test('invalid config (zero-width) → allow', () => {
|
||
expect(evaluateQuietHours({ start: 3, end: 3, tz })).toBe('allow');
|
||
});
|
||
|
||
test('invalid tz → allow (fail-open)', () => {
|
||
expect(evaluateQuietHours({ start: 22, end: 6, tz: 'Not/A_Real_TZ' })).toBe('allow');
|
||
});
|
||
|
||
test('straight-line window: inside → defer by default', () => {
|
||
// 02:00 UTC
|
||
const when = new Date(Date.UTC(2026, 0, 1, 2, 0, 0));
|
||
const cfg: QuietHoursConfig = { start: 1, end: 5, tz };
|
||
expect(evaluateQuietHours(cfg, when)).toBe('defer');
|
||
});
|
||
|
||
test('straight-line window: outside → allow', () => {
|
||
const when = new Date(Date.UTC(2026, 0, 1, 10, 0, 0));
|
||
const cfg: QuietHoursConfig = { start: 1, end: 5, tz };
|
||
expect(evaluateQuietHours(cfg, when)).toBe('allow');
|
||
});
|
||
|
||
test('straight-line window: end is exclusive', () => {
|
||
const when = new Date(Date.UTC(2026, 0, 1, 5, 0, 0));
|
||
const cfg: QuietHoursConfig = { start: 1, end: 5, tz };
|
||
expect(evaluateQuietHours(cfg, when)).toBe('allow');
|
||
});
|
||
|
||
test('wrap-around window: inside (after midnight) → defer', () => {
|
||
// 01:00 UTC, window 22:00 - 07:00
|
||
const when = new Date(Date.UTC(2026, 0, 1, 1, 0, 0));
|
||
const cfg: QuietHoursConfig = { start: 22, end: 7, tz };
|
||
expect(evaluateQuietHours(cfg, when)).toBe('defer');
|
||
});
|
||
|
||
test('wrap-around window: inside (before midnight) → defer', () => {
|
||
// 23:30 UTC, window 22:00 - 07:00
|
||
const when = new Date(Date.UTC(2026, 0, 1, 23, 30, 0));
|
||
const cfg: QuietHoursConfig = { start: 22, end: 7, tz };
|
||
expect(evaluateQuietHours(cfg, when)).toBe('defer');
|
||
});
|
||
|
||
test('wrap-around window: outside → allow', () => {
|
||
// 10:00 UTC, window 22:00 - 07:00
|
||
const when = new Date(Date.UTC(2026, 0, 1, 10, 0, 0));
|
||
const cfg: QuietHoursConfig = { start: 22, end: 7, tz };
|
||
expect(evaluateQuietHours(cfg, when)).toBe('allow');
|
||
});
|
||
|
||
test('policy "skip" returns skip verdict', () => {
|
||
const when = new Date(Date.UTC(2026, 0, 1, 2, 0, 0));
|
||
const cfg: QuietHoursConfig = { start: 1, end: 5, tz, policy: 'skip' };
|
||
expect(evaluateQuietHours(cfg, when)).toBe('skip');
|
||
});
|
||
|
||
test('timezone difference changes window position', () => {
|
||
// 14:00 UTC = 09:00 LA (PDT in summer). If the config is start:22 end:7 in LA,
|
||
// 14:00 UTC is outside → allow.
|
||
const when = new Date(Date.UTC(2026, 5, 15, 14, 0, 0)); // June → PDT
|
||
const cfg: QuietHoursConfig = { start: 22, end: 7, tz: 'America/Los_Angeles' };
|
||
expect(evaluateQuietHours(cfg, when)).toBe('allow');
|
||
});
|
||
|
||
test('timezone difference puts job inside window', () => {
|
||
// 06:00 UTC = 22:00 prev day in LA (summer, PDT offset -7).
|
||
// Wait — 06:00 UTC in June = 23:00 previous day LA (UTC-7).
|
||
// Config start:22 end:7 → 23:00 is inside → defer.
|
||
const when = new Date(Date.UTC(2026, 5, 15, 6, 0, 0));
|
||
const cfg: QuietHoursConfig = { start: 22, end: 7, tz: 'America/Los_Angeles' };
|
||
expect(evaluateQuietHours(cfg, when)).toBe('defer');
|
||
});
|
||
});
|
||
|
||
describe('localHour', () => {
|
||
test('UTC formatting matches Date.getUTCHours', () => {
|
||
const when = new Date(Date.UTC(2026, 0, 1, 15, 30, 0));
|
||
expect(localHour(when, 'UTC')).toBe(15);
|
||
});
|
||
|
||
test('invalid tz returns null', () => {
|
||
expect(localHour(new Date(), 'Not/Real')).toBeNull();
|
||
});
|
||
|
||
test('LA timezone shifts hour correctly (winter PST = UTC-8)', () => {
|
||
// Noon UTC in January = 04:00 LA
|
||
const when = new Date(Date.UTC(2026, 0, 1, 12, 0, 0));
|
||
expect(localHour(when, 'America/Los_Angeles')).toBe(4);
|
||
});
|
||
});
|
||
|
||
// ---------------------------------------------------------------------------
|
||
// Pure: staggerMinuteOffset
|
||
// ---------------------------------------------------------------------------
|
||
|
||
describe('staggerMinuteOffset', () => {
|
||
test('empty or non-string → 0', () => {
|
||
expect(staggerMinuteOffset('')).toBe(0);
|
||
// @ts-expect-error: runtime guard
|
||
expect(staggerMinuteOffset(null)).toBe(0);
|
||
});
|
||
|
||
test('returns 0–59', () => {
|
||
for (const k of ['social-radar', 'x-ingest', 'perplexity', 'sync-all']) {
|
||
const v = staggerMinuteOffset(k);
|
||
expect(v).toBeGreaterThanOrEqual(0);
|
||
expect(v).toBeLessThan(60);
|
||
}
|
||
});
|
||
|
||
test('deterministic: same key always same offset', () => {
|
||
const a = staggerMinuteOffset('social-radar');
|
||
const b = staggerMinuteOffset('social-radar');
|
||
expect(a).toBe(b);
|
||
});
|
||
|
||
test('different keys produce different offsets (most of the time)', () => {
|
||
const keys = ['a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j'];
|
||
const offsets = new Set(keys.map(staggerMinuteOffset));
|
||
// With 10 distinct keys and 60 buckets, expect at least 5 unique
|
||
// (collision rate stays well under 50% at this small sample size)
|
||
expect(offsets.size).toBeGreaterThanOrEqual(5);
|
||
});
|
||
|
||
test('second offset is 60x minute offset', () => {
|
||
const key = 'social-radar';
|
||
expect(staggerSecondOffset(key)).toBe(staggerMinuteOffset(key) * 60);
|
||
});
|
||
});
|
||
|
||
// ---------------------------------------------------------------------------
|
||
// Schema migration v12 applies
|
||
// ---------------------------------------------------------------------------
|
||
|
||
describe('schema migration v12 — minion_quiet_hours_stagger', () => {
|
||
let engine: BrainEngine;
|
||
let dbDir: string;
|
||
|
||
beforeAll(async () => {
|
||
dbDir = mkdtempSync(join(tmpdir(), 'm12-'));
|
||
engine = new PGLiteEngine();
|
||
await engine.connect({ engine: 'pglite', database_path: dbDir });
|
||
await engine.initSchema();
|
||
}, 60_000);
|
||
|
||
afterAll(async () => {
|
||
await engine.disconnect();
|
||
rmSync(dbDir, { recursive: true, force: true });
|
||
});
|
||
|
||
test('minion_jobs has quiet_hours column', async () => {
|
||
const rows = await engine.executeRaw<{ column_name: string }>(
|
||
`SELECT column_name FROM information_schema.columns
|
||
WHERE table_name = 'minion_jobs' AND column_name = 'quiet_hours'`,
|
||
);
|
||
expect(rows.length).toBe(1);
|
||
});
|
||
|
||
test('minion_jobs has stagger_key column', async () => {
|
||
const rows = await engine.executeRaw<{ column_name: string }>(
|
||
`SELECT column_name FROM information_schema.columns
|
||
WHERE table_name = 'minion_jobs' AND column_name = 'stagger_key'`,
|
||
);
|
||
expect(rows.length).toBe(1);
|
||
});
|
||
|
||
test('stagger_key index exists', async () => {
|
||
const rows = await engine.executeRaw<{ indexname: string }>(
|
||
`SELECT indexname FROM pg_indexes
|
||
WHERE tablename = 'minion_jobs' AND indexname = 'idx_minion_jobs_stagger_key'`,
|
||
);
|
||
expect(rows.length).toBe(1);
|
||
});
|
||
});
|