mirror of
https://github.com/garrytan/gbrain.git
synced 2026-08-16 18:02:30 +00:00
Compare commits
2
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
d98e6b507f | ||
|
|
d4bbf6eeae |
@@ -223,16 +223,14 @@ export GBRAIN_REMOTE_CLIENT_ID=<Alice's client_id>
|
||||
export GBRAIN_REMOTE_CLIENT_SECRET=<Alice's client_secret>
|
||||
export GBRAIN_REMOTE_MCP_URL=https://brain.acme-co.com/mcp
|
||||
|
||||
gbrain search "performance review"
|
||||
gbrain search "performance review" --remote
|
||||
```
|
||||
|
||||
(On a thin-client install every shared op routes through the remote MCP server automatically — no flag needed. The env vars select whose credentials the call uses.)
|
||||
|
||||
Alice should see results only from `customers` and `shared`. The performance-review notes live in `internal`, which she's not scoped to read. She shouldn't see them.
|
||||
|
||||
```bash
|
||||
# Terminal 2, as Bob (export his credentials similarly)
|
||||
gbrain search "performance review"
|
||||
gbrain search "performance review" --remote
|
||||
```
|
||||
|
||||
Bob should see the performance-review notes from `internal`, plus anything related from `shared`. He shouldn't see anything that lives only in `customers`.
|
||||
@@ -516,7 +514,7 @@ The first sync embeds every page, which takes time. Check `gbrain sources status
|
||||
|
||||
### "I see a page I shouldn't see"
|
||||
|
||||
This shouldn't happen, but if you suspect it, run `gbrain search <query> --json` as the constrained client (thin-client install, with the client's `GBRAIN_REMOTE_*` env exported) and inspect the `source_id` field on every returned result. Every row should be in the client's `--federated-read` set. If one isn't, file an issue with the exact slug and source IDs.
|
||||
This shouldn't happen, but if you suspect it, run `gbrain search <query> --remote --json` as the constrained client and inspect the `source_id` field on every returned result. Every row should be in the client's `--federated-read` set. If one isn't, file an issue with the exact slug and source IDs.
|
||||
|
||||
### "The synthesized answer is wrong"
|
||||
|
||||
|
||||
+5
-84
@@ -464,11 +464,7 @@ async function main() {
|
||||
// routed path. Date → ISO string; bigint → string (postgres.js shape);
|
||||
// Buffer → object. Microsecond-cost; eliminates a whole drift bug class.
|
||||
const result = JSON.parse(JSON.stringify(rawResult, bigintToStringReplacer));
|
||||
// #380 pass-through: `--json` (undeclared on most ops, promised by docs)
|
||||
// emits the raw op result instead of the human formatter.
|
||||
const output = params.json === true
|
||||
? JSON.stringify(result, null, 2) + '\n'
|
||||
: formatResult(op.name, result);
|
||||
const output = formatResult(op.name, result);
|
||||
if (output) process.stdout.write(output);
|
||||
} catch (e: unknown) {
|
||||
// v0.42.20.0 (codex D4): on error, set exitCode + return so the `finally`
|
||||
@@ -551,10 +547,7 @@ async function runThinClientRouted(
|
||||
signal: sigintController.signal,
|
||||
});
|
||||
const result = unpackToolResult(raw);
|
||||
// #380: same --json seam as the local-engine path (renderer parity).
|
||||
const output = params.json === true
|
||||
? JSON.stringify(result, null, 2) + '\n'
|
||||
: formatResult(op.name, result);
|
||||
const output = formatResult(op.name, result);
|
||||
if (output) process.stdout.write(output);
|
||||
} catch (e: unknown) {
|
||||
if (e instanceof RemoteMcpError) {
|
||||
@@ -764,28 +757,10 @@ export function resolveQueryImage(
|
||||
return { path: imagePath, base64, mime };
|
||||
}
|
||||
|
||||
/**
|
||||
* #380: undeclared flags that are honored DOWNSTREAM of parseOpArgs and must
|
||||
* keep passing through when unknown flags become hard errors:
|
||||
* - source → makeContext's resolveSourceId (the --source axis)
|
||||
* - brain → the mount/brain routing axis (docs promise the flag)
|
||||
* - dry_run → makeContext's ctx.dryRun (ops without a declared dry_run)
|
||||
* - json → raw-JSON output seam (local + thin-client paths)
|
||||
*/
|
||||
const PASSTHROUGH_VALUE_FLAGS = new Set(['source', 'brain']);
|
||||
const PASSTHROUGH_BOOL_FLAGS = new Set(['dry_run', 'json']);
|
||||
|
||||
export function parseOpArgs(op: Operation, args: string[]): Record<string, unknown> {
|
||||
const params: Record<string, unknown> = {};
|
||||
const positional = op.cliHints?.positional || [];
|
||||
let posIdx = 0;
|
||||
const cliName = op.cliHints?.name || op.name;
|
||||
const MAX_STDIN = 5_000_000; // 5MB cap, shared by stdin and --file
|
||||
// #380: `--file <path>` fills the op's declared stdin param (put's `content`)
|
||||
// from a file. Driven by cliHints.stdin — no per-op hard-coding — and
|
||||
// disabled when the op declares a real `file` param of its own.
|
||||
const fileParam = op.cliHints?.stdin && !op.params.file ? op.cliHints.stdin : undefined;
|
||||
let filePath: string | undefined;
|
||||
|
||||
for (let i = 0; i < args.length; i++) {
|
||||
const arg = args[i];
|
||||
@@ -799,42 +774,12 @@ export function parseOpArgs(op: Operation, args: string[]): Record<string, unkno
|
||||
}
|
||||
}
|
||||
const key = arg.slice(2).replace(/-/g, '_');
|
||||
if (fileParam && key === 'file') {
|
||||
if (i + 1 >= args.length) {
|
||||
console.error(`Error: ${arg} requires a value.`);
|
||||
process.exit(1);
|
||||
}
|
||||
filePath = args[++i];
|
||||
continue;
|
||||
}
|
||||
const paramDef = op.params[key];
|
||||
if (!paramDef) {
|
||||
if (PASSTHROUGH_BOOL_FLAGS.has(key)) {
|
||||
params[key] = true;
|
||||
continue;
|
||||
}
|
||||
if (PASSTHROUGH_VALUE_FLAGS.has(key)) {
|
||||
if (i + 1 >= args.length) {
|
||||
console.error(`Error: ${arg} requires a value.`);
|
||||
process.exit(1);
|
||||
}
|
||||
params[key] = args[++i];
|
||||
continue;
|
||||
}
|
||||
// #380: unknown flags were silently swallowed into params, so typos
|
||||
// like `put --file` created empty pages instead of erroring.
|
||||
console.error(`Unknown option for gbrain ${cliName}: ${arg}`);
|
||||
console.error(`Run 'gbrain ${cliName} --help' for valid flags.`);
|
||||
process.exit(1);
|
||||
}
|
||||
if (paramDef.type === 'boolean') {
|
||||
if (paramDef?.type === 'boolean') {
|
||||
params[key] = true;
|
||||
} else if (i + 1 < args.length) {
|
||||
params[key] = args[++i];
|
||||
if (paramDef.type === 'number') params[key] = Number(params[key]);
|
||||
} else {
|
||||
console.error(`Error: ${arg} requires a value.`);
|
||||
process.exit(1);
|
||||
if (paramDef?.type === 'number') params[key] = Number(params[key]);
|
||||
}
|
||||
} else if (posIdx < positional.length) {
|
||||
const key = positional[posIdx++];
|
||||
@@ -843,30 +788,10 @@ export function parseOpArgs(op: Operation, args: string[]): Record<string, unkno
|
||||
}
|
||||
}
|
||||
|
||||
// #380: resolve --file AFTER the loop so --file/--content conflicts are
|
||||
// caught in either order.
|
||||
if (filePath !== undefined && fileParam) {
|
||||
if (params[fileParam] !== undefined) {
|
||||
console.error(`Error: use only one of --file, --${fileParam}, or stdin for gbrain ${cliName}.`);
|
||||
process.exit(1);
|
||||
}
|
||||
let fileContent: string;
|
||||
try {
|
||||
fileContent = readFileSync(filePath, 'utf-8');
|
||||
} catch (e) {
|
||||
console.error(`Error: cannot read --file ${filePath}: ${e instanceof Error ? e.message : String(e)}`);
|
||||
process.exit(1);
|
||||
}
|
||||
if (Buffer.byteLength(fileContent, 'utf-8') > MAX_STDIN) {
|
||||
console.error(`Error: file content exceeds ${MAX_STDIN} bytes. Split into smaller inputs.`);
|
||||
process.exit(1);
|
||||
}
|
||||
params[fileParam] = fileContent;
|
||||
}
|
||||
|
||||
// Read stdin for content params
|
||||
if (op.cliHints?.stdin && !params[op.cliHints.stdin] && !process.stdin.isTTY) {
|
||||
const stdinContent = readFileSync(0, 'utf-8');
|
||||
const MAX_STDIN = 5_000_000; // 5MB
|
||||
if (Buffer.byteLength(stdinContent, 'utf-8') > MAX_STDIN) {
|
||||
console.error(`Error: stdin content exceeds ${MAX_STDIN} bytes. Split into smaller inputs.`);
|
||||
process.exit(1);
|
||||
@@ -2328,10 +2253,6 @@ export function printOpHelp(op: Operation, invokedName?: string) {
|
||||
const prefix = isPos ? ` <${key}>` : ` --${key.replace(/_/g, '-')}`;
|
||||
console.log(`${prefix.padEnd(28)} ${def.description || ''}${req}`);
|
||||
}
|
||||
// #380: ops that read stdin also accept --file <path> (parseOpArgs).
|
||||
if (op.cliHints?.stdin && !op.params.file) {
|
||||
console.log(`${' --file <path>'.padEnd(28)} Read ${op.cliHints.stdin} from a file (alternative to --${op.cliHints.stdin} or stdin)`);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -769,7 +769,7 @@ const get_page: Operation = {
|
||||
|
||||
const put_page: Operation = {
|
||||
name: 'put_page',
|
||||
description: 'Write/update a page (markdown with frontmatter). Chunks, embeds, reconciles tags, and (when auto_link/auto_timeline are enabled) extracts + reconciles graph links and timeline entries. On the CLI, `gbrain put SLUG --file PATH` reads content from a file (also `--content` or stdin). For provenance write-through and a binary-NUL guard, prefer `gbrain capture --file PATH --slug SLUG` (v0.39.3.0).',
|
||||
description: 'Write/update a page (markdown with frontmatter). Chunks, embeds, reconciles tags, and (when auto_link/auto_timeline are enabled) extracts + reconciles graph links and timeline entries. For large content on Windows (pipe-buffer limit ~45KB) or any file-as-input workflow, use `gbrain capture --file PATH --slug SLUG` — capture reads the file as a Buffer with a binary-NUL guard and adds provenance write-through (v0.39.3.0).',
|
||||
params: {
|
||||
slug: { type: 'string', required: true, description: 'Page slug' },
|
||||
content: { type: 'string', required: true, description: 'Full markdown content with YAML frontmatter' },
|
||||
@@ -1384,10 +1384,7 @@ const list_pages: Operation = {
|
||||
params: {
|
||||
type: { type: 'string', description: 'Filter by page type' },
|
||||
tag: { type: 'string', description: 'Filter by tag' },
|
||||
limit: { type: 'number', description: 'Max results (default 50, capped at 100 — use offset to paginate beyond)' },
|
||||
// #2876: the 100-row cap was silent and there was no way past it even
|
||||
// though both engines already support OFFSET on listPages.
|
||||
offset: { type: 'number', description: 'Skip first N results (pagination; pair with limit)' },
|
||||
limit: { type: 'number', description: 'Max results (default 50)' },
|
||||
// v0.29 — surface filter that already exists on PageFilters.
|
||||
updated_after: {
|
||||
type: 'string',
|
||||
@@ -1418,10 +1415,6 @@ const list_pages: Operation = {
|
||||
type: p.type as any,
|
||||
tag: p.tag as string,
|
||||
limit: clampSearchLimit(p.limit as number | undefined, 50, 100),
|
||||
// #2876: thread pagination through (engines already honor offset).
|
||||
offset: Number.isFinite(p.offset as number) && (p.offset as number) > 0
|
||||
? Math.floor(p.offset as number)
|
||||
: undefined,
|
||||
includeDeleted: (p.include_deleted as boolean) === true,
|
||||
updated_after: typeof p.updated_after === 'string' ? p.updated_after : undefined,
|
||||
sort,
|
||||
|
||||
@@ -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[]> {
|
||||
|
||||
@@ -1,41 +1,8 @@
|
||||
import { describe, expect, test } from 'bun:test';
|
||||
import { mkdtempSync, rmSync, writeFileSync } from 'fs';
|
||||
import { tmpdir } from 'os';
|
||||
import { join } from 'path';
|
||||
import { parseOpArgs } from '../src/cli.ts';
|
||||
import { operationsByName } from '../src/core/operations.ts';
|
||||
|
||||
describe('parseOpArgs', () => {
|
||||
// #380: `gbrain put SLUG --file PATH` reads content from the file instead
|
||||
// of silently swallowing the flag and creating an empty page.
|
||||
test('put --file reads the stdin param (content) from a file', () => {
|
||||
const dir = mkdtempSync(join(tmpdir(), 'gbrain-put-file-'));
|
||||
try {
|
||||
const pagePath = join(dir, 'page.md');
|
||||
writeFileSync(pagePath, '# From file\n\nBody loaded from --file.\n');
|
||||
const params = parseOpArgs(operationsByName.put_page, ['concepts/from-file', '--file', pagePath]);
|
||||
expect(params.slug).toBe('concepts/from-file');
|
||||
expect(params.content).toBe('# From file\n\nBody loaded from --file.\n');
|
||||
} finally {
|
||||
rmSync(dir, { recursive: true, force: true });
|
||||
}
|
||||
});
|
||||
|
||||
// #380 regression guard: undeclared-but-honored flags must keep passing
|
||||
// through when unknown flags become hard errors (--source is read by
|
||||
// makeContext; --json by the output seam; --dry-run by ctx.dryRun).
|
||||
test('pass-through allowlist flags survive on ops that do not declare them', () => {
|
||||
const params = parseOpArgs(operationsByName.get_page, [
|
||||
'people/alice-example', '--source', 'wiki', '--json', '--dry-run',
|
||||
]);
|
||||
expect(params).toEqual({
|
||||
slug: 'people/alice-example',
|
||||
source: 'wiki',
|
||||
json: true,
|
||||
dry_run: true,
|
||||
});
|
||||
});
|
||||
|
||||
test('--no-<boolean> maps to false without consuming the next flag', () => {
|
||||
const params = parseOpArgs(operationsByName.query, [
|
||||
'freshEmbedSourceScope code source',
|
||||
|
||||
+1
-71
@@ -1,5 +1,5 @@
|
||||
import { describe, test, expect } from 'bun:test';
|
||||
import { existsSync, mkdtempSync, readFileSync, rmSync, writeFileSync } from 'fs';
|
||||
import { existsSync, mkdtempSync, readFileSync, rmSync } from 'fs';
|
||||
import { tmpdir } from 'os';
|
||||
import { join } from 'path';
|
||||
|
||||
@@ -120,76 +120,6 @@ describe('CLI dispatch integration', () => {
|
||||
expect(exitCode).toBe(0);
|
||||
});
|
||||
|
||||
// #380 / PR #856: put --help documents the --file input path.
|
||||
test('put --help documents --file input', async () => {
|
||||
const proc = Bun.spawn(['bun', 'run', 'src/cli.ts', 'put', '--help'], {
|
||||
cwd: repoRoot,
|
||||
stdout: 'pipe',
|
||||
stderr: 'pipe',
|
||||
});
|
||||
const stdout = await new Response(proc.stdout).text();
|
||||
const exitCode = await proc.exited;
|
||||
expect(stdout).toContain('Usage: gbrain put');
|
||||
expect(stdout).toContain('--file <path>');
|
||||
expect(exitCode).toBe(0);
|
||||
});
|
||||
|
||||
// #380: unknown flags on shared ops are a hard error (previously silently
|
||||
// swallowed into params — `put --file` created empty pages). parseOpArgs
|
||||
// runs BEFORE engine connect, so the error must fire without a brain.
|
||||
test('unknown shared-op flags fail before DB connection', async () => {
|
||||
const home = mkdtempSync(join(tmpdir(), 'gbrain-cli-unknown-flag-'));
|
||||
try {
|
||||
const proc = Bun.spawn(['bun', 'run', 'src/cli.ts', 'get', 'people/alice', '--bogus'], {
|
||||
cwd: repoRoot,
|
||||
stdout: 'pipe',
|
||||
stderr: 'pipe',
|
||||
env: isolatedEnv(home),
|
||||
});
|
||||
const stderr = await new Response(proc.stderr).text();
|
||||
const exitCode = await proc.exited;
|
||||
expect(stderr).toContain('Unknown option for gbrain get: --bogus');
|
||||
expect(stderr).not.toContain('No brain configured');
|
||||
expect(exitCode).toBe(1);
|
||||
} finally {
|
||||
rmSync(home, { recursive: true, force: true });
|
||||
}
|
||||
});
|
||||
|
||||
test('put rejects combining --file and --content', async () => {
|
||||
const home = mkdtempSync(join(tmpdir(), 'gbrain-cli-put-conflict-'));
|
||||
try {
|
||||
const pagePath = join(home, 'page.md');
|
||||
writeFileSync(pagePath, 'file body\n');
|
||||
const proc = Bun.spawn(
|
||||
['bun', 'run', 'src/cli.ts', 'put', 'a/b', '--content', 'inline', '--file', pagePath],
|
||||
{ cwd: repoRoot, stdout: 'pipe', stderr: 'pipe', env: isolatedEnv(home) },
|
||||
);
|
||||
const stderr = await new Response(proc.stderr).text();
|
||||
const exitCode = await proc.exited;
|
||||
expect(stderr).toContain('use only one of --file, --content, or stdin');
|
||||
expect(exitCode).toBe(1);
|
||||
} finally {
|
||||
rmSync(home, { recursive: true, force: true });
|
||||
}
|
||||
});
|
||||
|
||||
test('put --file with a missing path errors instead of writing an empty page', async () => {
|
||||
const home = mkdtempSync(join(tmpdir(), 'gbrain-cli-put-missing-file-'));
|
||||
try {
|
||||
const proc = Bun.spawn(
|
||||
['bun', 'run', 'src/cli.ts', 'put', 'a/b', '--file', join(home, 'nope.md')],
|
||||
{ cwd: repoRoot, stdout: 'pipe', stderr: 'pipe', env: isolatedEnv(home) },
|
||||
);
|
||||
const stderr = await new Response(proc.stderr).text();
|
||||
const exitCode = await proc.exited;
|
||||
expect(stderr).toContain('cannot read --file');
|
||||
expect(exitCode).toBe(1);
|
||||
} finally {
|
||||
rmSync(home, { recursive: true, force: true });
|
||||
}
|
||||
});
|
||||
|
||||
test('upgrade --help prints usage without running upgrade', async () => {
|
||||
const proc = Bun.spawn(['bun', 'run', 'src/cli.ts', 'upgrade', '--help'], {
|
||||
cwd: repoRoot,
|
||||
|
||||
@@ -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');
|
||||
|
||||
|
||||
@@ -1,55 +0,0 @@
|
||||
import { describe, test, expect } from 'bun:test';
|
||||
import { operationsByName } from '../src/core/operations.ts';
|
||||
|
||||
/**
|
||||
* #2876: `gbrain list --limit` silently clamped at 100 with no pagination.
|
||||
* list_pages now declares `offset` (both engines already supported it on
|
||||
* PageFilters) and the limit description discloses the 100-row cap.
|
||||
*/
|
||||
describe('list_pages pagination (#2876)', () => {
|
||||
const listPagesOp = operationsByName.list_pages;
|
||||
|
||||
function makeCtx(captured: unknown[]) {
|
||||
return {
|
||||
engine: {
|
||||
listPages: async (filters: unknown) => {
|
||||
captured.push(filters);
|
||||
return [];
|
||||
},
|
||||
},
|
||||
config: { engine: 'pglite' },
|
||||
logger: { info() {}, warn() {}, error() {} },
|
||||
dryRun: false,
|
||||
remote: false,
|
||||
sourceId: 'default',
|
||||
} as any;
|
||||
}
|
||||
|
||||
test('declares offset param and discloses the 100-row cap on limit', () => {
|
||||
expect(listPagesOp.params.offset).toBeDefined();
|
||||
expect(listPagesOp.params.offset.type).toBe('number');
|
||||
expect(listPagesOp.params.limit.description).toContain('100');
|
||||
});
|
||||
|
||||
test('threads offset through to engine.listPages', async () => {
|
||||
const captured: any[] = [];
|
||||
await listPagesOp.handler(makeCtx(captured), { limit: 10, offset: 30 });
|
||||
expect(captured[0].offset).toBe(30);
|
||||
expect(captured[0].limit).toBe(10);
|
||||
});
|
||||
|
||||
test('drops negative, non-finite, and zero offsets', async () => {
|
||||
const captured: any[] = [];
|
||||
const ctx = makeCtx(captured);
|
||||
await listPagesOp.handler(ctx, { offset: -5 });
|
||||
await listPagesOp.handler(ctx, { offset: Infinity });
|
||||
await listPagesOp.handler(ctx, { offset: 0 });
|
||||
for (const f of captured) expect(f.offset).toBeUndefined();
|
||||
});
|
||||
|
||||
test('floors fractional offsets', async () => {
|
||||
const captured: any[] = [];
|
||||
await listPagesOp.handler(makeCtx(captured), { offset: 7.9 });
|
||||
expect(captured[0].offset).toBe(7);
|
||||
});
|
||||
});
|
||||
@@ -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
|
||||
});
|
||||
|
||||
Reference in New Issue
Block a user