mirror of
https://github.com/garrytan/gbrain.git
synced 2026-08-16 09:52:22 +00:00
Compare commits
3
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
d1f03cb346 | ||
|
|
e41e3948cd | ||
|
|
edad6b1d5f |
@@ -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)`);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -38,6 +38,7 @@ import { logSelfUpgrade } from '../core/audit/self-upgrade-audit.ts';
|
||||
import { detectInstallMethod } from './upgrade.ts';
|
||||
import { evaluateQuietHours } from '../core/minions/quiet-hours.ts';
|
||||
import { inspectLock } from '../core/db-lock.ts';
|
||||
import { registerCleanup } from '../core/process-cleanup.ts';
|
||||
|
||||
/**
|
||||
* v0.37.7.0 #1162 — classify autopilot reconnect-loop errors.
|
||||
@@ -433,6 +434,37 @@ export async function runAutopilot(engine: BrainEngine, args: string[]) {
|
||||
let stopping = false;
|
||||
let childSupervisor: ChildWorkerSupervisor | null = null;
|
||||
|
||||
// #1872: graceful engine shutdown. On PGLite the cycle steps run INLINE in
|
||||
// this process, so a hard `process.exit` mid-write (systemctl stop →
|
||||
// SIGTERM) kills WASM Postgres with the WAL dirty and can corrupt the
|
||||
// brain. Two exit paths must both close the engine:
|
||||
// - autopilot's own shutdown() below (owns SIGINT + internal stops like
|
||||
// max_crashes / cycle-failure-cap), and
|
||||
// - process-cleanup's SIGTERM handler (installed at cli.ts module load;
|
||||
// it runs the cleanup registry with a 3s deadline and then exits) —
|
||||
// which is why closeEngine is ALSO registered there.
|
||||
// closeEngine aborts the in-flight inline cycle (runCycle checks the
|
||||
// signal between phases and threads it into phase sub-work), gives it a
|
||||
// short bounded window to wind down, then disconnects. PGLite's
|
||||
// disconnect() drains the pending query and checkpoints before closing;
|
||||
// a second call is a no-op (disconnect snapshots + nulls the handle), so
|
||||
// both paths firing is safe.
|
||||
const shutdownAbort = new AbortController();
|
||||
let inflightInlineCycle: Promise<unknown> | null = null;
|
||||
const closeEngine = async () => {
|
||||
shutdownAbort.abort(new Error('autopilot shutdown'));
|
||||
if (inflightInlineCycle) {
|
||||
// ponytail: 2s cap keeps us inside process-cleanup's 3s deadline; a
|
||||
// between-phase abort resolves instantly, a mid-phase one may not.
|
||||
await Promise.race([
|
||||
inflightInlineCycle.catch(() => { /* cycle errors already logged by the loop */ }),
|
||||
new Promise((r) => setTimeout(r, 2_000)),
|
||||
]);
|
||||
}
|
||||
try { await engine.disconnect(); } catch { /* best-effort */ }
|
||||
};
|
||||
const deregisterEngineClose = registerCleanup('autopilot-engine-close', closeEngine);
|
||||
|
||||
if (spawnManagedWorker) {
|
||||
const cliPath = resolveGbrainCliPath();
|
||||
// Cgroup-aware auto-sized RSS watchdog cap (issue #1678). The old flat
|
||||
@@ -520,6 +552,10 @@ export async function runAutopilot(engine: BrainEngine, args: string[]) {
|
||||
childSupervisor.killChild('SIGKILL');
|
||||
}
|
||||
}
|
||||
// #1872: abort the in-flight inline cycle and close the engine BEFORE
|
||||
// process.exit — a hard exit mid-write corrupts PGLite's WASM Postgres.
|
||||
await closeEngine();
|
||||
deregisterEngineClose();
|
||||
try { unlinkSync(lockPath); } catch { /* already gone */ }
|
||||
process.exit(0);
|
||||
};
|
||||
@@ -1008,16 +1044,21 @@ export async function runAutopilot(engine: BrainEngine, args: string[]) {
|
||||
// path's phase set). Now both converge on the same primitive.
|
||||
try {
|
||||
const { runCycle } = await import('../core/cycle.ts');
|
||||
const report = await runCycle(engine, {
|
||||
// #1872: track the promise so closeEngine can drain it on shutdown,
|
||||
// and pass the abort signal so the cycle winds down between phases.
|
||||
const cyclePromise = runCycle(engine, {
|
||||
brainDir: repoPath,
|
||||
// Autopilot daemon path: pulls by default (matches
|
||||
// pre-v0.17 autopilot behavior). CLI dream defaults false
|
||||
// for cron safety; that choice is scoped to dream only.
|
||||
pull: true,
|
||||
signal: shutdownAbort.signal,
|
||||
yieldBetweenPhases: async () => {
|
||||
await new Promise(r => setImmediate(r));
|
||||
},
|
||||
});
|
||||
inflightInlineCycle = cyclePromise;
|
||||
const report = await cyclePromise.finally(() => { inflightInlineCycle = null; });
|
||||
// Only 'failed' (every attempted phase failed) trips the autopilot
|
||||
// circuit breaker. 'partial' means at least one phase warned or
|
||||
// failed while others ran — that's a soft signal, not a fatal
|
||||
|
||||
+23
-3
@@ -26,6 +26,7 @@
|
||||
import type { BrainEngine } from '../core/engine.ts';
|
||||
import {
|
||||
runCycle,
|
||||
resolveSourceForDir,
|
||||
ALL_PHASES,
|
||||
type CyclePhase,
|
||||
type CycleReport,
|
||||
@@ -380,9 +381,9 @@ Options:
|
||||
|
||||
--source <id> Scope the cycle to one source so doctor's
|
||||
cycle_freshness check sees a fresh stamp on
|
||||
completion. Without this, gbrain dream's
|
||||
timestamp never lands and federated brains
|
||||
see "stale cycle" forever.
|
||||
completion. When omitted, gbrain derives the
|
||||
source from --dir / the configured checkout
|
||||
when it matches a source's local_path (#1869).
|
||||
--source-id <id> Alias for --source. Matches the v0.37.7.0+
|
||||
naming used by import/extract/graph-query.
|
||||
|
||||
@@ -634,6 +635,25 @@ export async function runDream(engine: BrainEngine | null, args: string[]): Prom
|
||||
);
|
||||
process.exit(1);
|
||||
}
|
||||
|
||||
// #1869: a path-scoped run (--dir, or the configured sync.repo_path) whose
|
||||
// directory matches a registered source's local_path IS that source's cycle
|
||||
// — derive the source id so runCycle writes last_source_cycle_at /
|
||||
// last_full_cycle_at on success and doctor's cycle_freshness check stops
|
||||
// reading perpetually stale. Explicit --source still wins (resolved above).
|
||||
// Fixed here at the command level, NOT in runCycle's stamp gate, so legacy
|
||||
// global callers (autopilot-global-maintenance runs GLOBAL_PHASES with a
|
||||
// brainDir and no sourceId) can't falsely stamp per-source freshness.
|
||||
// A derived match on an archived source is skipped silently (falls back to
|
||||
// legacy unscoped behavior) — stamping it would mask staleness on restore,
|
||||
// mirroring the explicit --source archived guard above.
|
||||
if (resolvedSourceId === undefined && engine !== null && brainDir !== null) {
|
||||
const derived = await resolveSourceForDir(engine, brainDir);
|
||||
if (derived !== undefined) {
|
||||
const src = await fetchSource(engine, derived);
|
||||
if (src?.archived !== true) resolvedSourceId = derived;
|
||||
}
|
||||
}
|
||||
// ─── issue #1678: bounded single-hold extract_atoms drain ──────────
|
||||
if (opts.drain) {
|
||||
if (engine === null) {
|
||||
|
||||
+9
-1
@@ -855,8 +855,16 @@ interface SyncPhaseResult extends PhaseResult {
|
||||
* Resolve the source id for a brain directory by looking up the sources
|
||||
* table. Returns undefined when no registered source matches (falls back
|
||||
* to pre-v0.18 global config.sync.* keys).
|
||||
*
|
||||
* Exported for dream.ts (#1869): a `gbrain dream --dir <path>` run whose
|
||||
* path matches a registered source's local_path is a per-source cycle in
|
||||
* everything but name, so dream derives the source id up front and passes
|
||||
* it as opts.sourceId — landing the freshness stamp without changing
|
||||
* runCycle's stamp/lock semantics for legacy global callers (the
|
||||
* autopilot-global-maintenance handler runs GLOBAL_PHASES with a brainDir
|
||||
* and MUST NOT stamp per-source freshness; see rejected PR #2549).
|
||||
*/
|
||||
async function resolveSourceForDir(
|
||||
export async function resolveSourceForDir(
|
||||
engine: BrainEngine,
|
||||
brainDir: string | null,
|
||||
): Promise<string | undefined> {
|
||||
|
||||
@@ -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,
|
||||
|
||||
@@ -0,0 +1,63 @@
|
||||
/**
|
||||
* #1872 — autopilot SIGTERM/SIGINT must close the engine before exit.
|
||||
*
|
||||
* On PGLite the cycle steps run INLINE in the autopilot process, so a hard
|
||||
* `process.exit` mid-write (systemctl stop → SIGTERM) kills WASM Postgres
|
||||
* with the WAL dirty and can corrupt the brain. Two exit paths must both
|
||||
* close the engine:
|
||||
*
|
||||
* - autopilot's own shutdown() (owns SIGINT + internal stops like
|
||||
* max_crashes / cycle-failure-cap), and
|
||||
* - process-cleanup's SIGTERM handler (installed at cli.ts module load,
|
||||
* which exits within its 3s cleanup deadline) — reached via the
|
||||
* registered 'autopilot-engine-close' cleanup callback.
|
||||
*
|
||||
* Because the shutdown path is deep inside `runAutopilot()` (a long-running
|
||||
* daemon loop that ends in process.exit), a behavioral test would have to
|
||||
* spawn + signal a real daemon. Following the established precedent
|
||||
* (test/autopilot-supervisor-wiring.test.ts, test/autopilot-fanout-wiring.test.ts),
|
||||
* these static-shape regressions pin the load-bearing wiring instead.
|
||||
*/
|
||||
import { describe, expect, it } from 'bun:test';
|
||||
import { readFileSync } from 'fs';
|
||||
import { join } from 'path';
|
||||
|
||||
const AUTOPILOT_SRC = readFileSync(
|
||||
join(import.meta.dir, '..', 'src', 'commands', 'autopilot.ts'),
|
||||
'utf8',
|
||||
);
|
||||
|
||||
describe('autopilot.ts graceful engine shutdown (#1872)', () => {
|
||||
it('registers an engine-close callback in the process-cleanup registry (SIGTERM path)', () => {
|
||||
// process-cleanup owns SIGTERM (installed at cli.ts:10) and hard-exits
|
||||
// after its cleanup pass; without this registration the engine is never
|
||||
// closed on `systemctl stop`.
|
||||
expect(AUTOPILOT_SRC).toContain(
|
||||
"import { registerCleanup } from '../core/process-cleanup.ts';",
|
||||
);
|
||||
expect(AUTOPILOT_SRC).toContain(
|
||||
"registerCleanup('autopilot-engine-close', closeEngine)",
|
||||
);
|
||||
});
|
||||
|
||||
it('closeEngine aborts the in-flight inline cycle then disconnects the engine', () => {
|
||||
// Abort first (runCycle checks the signal between phases and threads it
|
||||
// into phase sub-work), bounded drain, then disconnect.
|
||||
expect(AUTOPILOT_SRC).toMatch(
|
||||
/const closeEngine = async \(\) => \{[\s\S]{0,900}shutdownAbort\.abort\([\s\S]{0,900}engine\.disconnect\(\)/,
|
||||
);
|
||||
});
|
||||
|
||||
it('the inline runCycle call carries the shutdown abort signal and is tracked as in-flight', () => {
|
||||
// PGLite / --inline path: the cycle runs in-process, so shutdown must be
|
||||
// able to (a) signal it to wind down and (b) await it before closing.
|
||||
expect(AUTOPILOT_SRC).toMatch(/signal:\s*shutdownAbort\.signal/);
|
||||
expect(AUTOPILOT_SRC).toMatch(/inflightInlineCycle\s*=\s*cyclePromise/);
|
||||
});
|
||||
|
||||
it('shutdown() awaits closeEngine() before process.exit(0) (SIGINT + internal-stop path)', () => {
|
||||
expect(AUTOPILOT_SRC).toMatch(
|
||||
/await closeEngine\(\);[\s\S]{0,400}process\.exit\(0\)/,
|
||||
);
|
||||
});
|
||||
});
|
||||
@@ -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,
|
||||
|
||||
@@ -0,0 +1,99 @@
|
||||
/**
|
||||
* #1869 — `gbrain dream --dir <path>` stamps cycle freshness when the path
|
||||
* matches a registered source's local_path.
|
||||
*
|
||||
* Pre-fix, only `--source <id>` runs wrote last_source_cycle_at /
|
||||
* last_full_cycle_at (runCycle's stamp gate reads opts.sourceId, and dream
|
||||
* never derived one from --dir), so a path-scoped brain showed doctor's
|
||||
* cycle_freshness as perpetually stale.
|
||||
*
|
||||
* The fix lives in dream.ts (derive the source id from the resolved brain
|
||||
* dir via resolveSourceForDir), NOT in runCycle's stamp gate — a runCycle-
|
||||
* wide change would make the autopilot-global-maintenance handler (global
|
||||
* phases, brainDir set, no sourceId) falsely stamp per-source freshness
|
||||
* (the #2194 poisoning class; see rejected PR #2549).
|
||||
*
|
||||
* Same real-PGLite/no-mocks discipline as test/dream.test.ts; same
|
||||
* GBRAIN_HOME isolation as test/cycle-last-full-cycle-at.test.ts (the
|
||||
* cycle's PGLite file lock lives under ~/.gbrain).
|
||||
*/
|
||||
import { describe, test, expect, beforeAll, afterAll, beforeEach, afterEach } from 'bun:test';
|
||||
import { mkdtempSync, rmSync } from 'fs';
|
||||
import { join } from 'path';
|
||||
import { tmpdir } from 'os';
|
||||
import { PGLiteEngine } from '../src/core/pglite-engine.ts';
|
||||
import { resetPgliteState } from './helpers/reset-pglite.ts';
|
||||
import { runDream } from '../src/commands/dream.ts';
|
||||
import { withEnv } from './helpers/with-env.ts';
|
||||
|
||||
let engine: PGLiteEngine;
|
||||
let brainDir: string;
|
||||
let gbrainHome: string;
|
||||
|
||||
beforeAll(async () => {
|
||||
engine = new PGLiteEngine();
|
||||
await engine.connect({});
|
||||
await engine.initSchema();
|
||||
}, 60_000);
|
||||
|
||||
afterAll(async () => {
|
||||
await engine.disconnect();
|
||||
});
|
||||
|
||||
beforeEach(async () => {
|
||||
await resetPgliteState(engine);
|
||||
brainDir = mkdtempSync(join(tmpdir(), 'gbrain-dream-stamp-'));
|
||||
gbrainHome = mkdtempSync(join(tmpdir(), 'gbrain-dream-stamp-home-'));
|
||||
}, 60_000);
|
||||
|
||||
afterEach(() => {
|
||||
rmSync(brainDir, { recursive: true, force: true });
|
||||
rmSync(gbrainHome, { recursive: true, force: true });
|
||||
});
|
||||
|
||||
async function seedSource(id: string, archived = false): Promise<void> {
|
||||
await engine.executeRaw(
|
||||
`INSERT INTO sources (id, name, local_path, config, archived, created_at)
|
||||
VALUES ($1, $2, $3, '{}'::jsonb, $4, NOW())`,
|
||||
[id, id, brainDir, archived],
|
||||
);
|
||||
}
|
||||
|
||||
async function readLastFullCycleAt(sourceId: string): Promise<string | null> {
|
||||
const rows = await engine.executeRaw<{ config: Record<string, unknown> | null }>(
|
||||
`SELECT config FROM sources WHERE id = $1`,
|
||||
[sourceId],
|
||||
);
|
||||
const raw = rows[0]?.config?.last_full_cycle_at;
|
||||
return typeof raw === 'string' ? raw : null;
|
||||
}
|
||||
|
||||
describe('gbrain dream --dir <path> freshness stamp (#1869)', () => {
|
||||
test('--dir matching a source local_path stamps last_full_cycle_at', async () => {
|
||||
await withEnv({ GBRAIN_HOME: gbrainHome }, async () => {
|
||||
await seedSource('path-scoped');
|
||||
expect(await readLastFullCycleAt('path-scoped')).toBeNull();
|
||||
|
||||
const report = await runDream(engine, ['--dir', brainDir, '--phase', 'lint', '--json']);
|
||||
expect(report).toBeTruthy();
|
||||
if (report) expect(['ok', 'clean']).toContain(report.status);
|
||||
|
||||
// Pre-fix this stays null forever: dream never passed a sourceId, so
|
||||
// runCycle's stamp gate skipped the write.
|
||||
expect(await readLastFullCycleAt('path-scoped')).not.toBeNull();
|
||||
});
|
||||
}, 60_000);
|
||||
|
||||
test('--dir matching an ARCHIVED source does not stamp it', async () => {
|
||||
await withEnv({ GBRAIN_HOME: gbrainHome }, async () => {
|
||||
await seedSource('mothballed', true);
|
||||
|
||||
const report = await runDream(engine, ['--dir', brainDir, '--phase', 'lint', '--json']);
|
||||
expect(report).toBeTruthy();
|
||||
|
||||
// Stamping an archived source would mask data staleness when it is
|
||||
// later restored (mirrors the explicit --source archived guard).
|
||||
expect(await readLastFullCycleAt('mothballed')).toBeNull();
|
||||
});
|
||||
}, 60_000);
|
||||
});
|
||||
+14
-4
@@ -562,12 +562,22 @@ describe('runDream — --source / --source-id (v0.41.13)', () => {
|
||||
|
||||
// ─── Back-compat: bare `gbrain dream` does NOT write per-source stamp ─
|
||||
|
||||
test('gbrain dream (no --source) leaves all sources untouched (back-compat regression)', async () => {
|
||||
await seedSource('alpha');
|
||||
await seedSource('beta');
|
||||
test('gbrain dream (no --source) stamps only the source whose local_path matches --dir (#1869)', async () => {
|
||||
// Pre-#1869 this asserted NO source was ever stamped without an explicit
|
||||
// --source — which is exactly the bug: a path-scoped `gbrain dream --dir`
|
||||
// run never landed a freshness stamp and doctor's cycle_freshness stayed
|
||||
// stale forever. New truth: the source whose local_path matches the
|
||||
// resolved brain dir is derived and stamped; unrelated sources stay
|
||||
// untouched (cross-source isolation).
|
||||
await seedSource('alpha'); // local_path = repo → derived + stamped
|
||||
await engine.executeRaw(
|
||||
`INSERT INTO sources (id, name, local_path, config, archived, created_at)
|
||||
VALUES ($1, $2, $3, '{}'::jsonb, false, NOW())`,
|
||||
['beta', 'beta', '/somewhere/else'],
|
||||
);
|
||||
const report = await runDream(engine, ['--dir', repo, '--phase', 'lint', '--json']);
|
||||
expect(report).toBeTruthy();
|
||||
expect(await readLastFullCycleAt('alpha')).toBeNull();
|
||||
expect(await readLastFullCycleAt('alpha')).not.toBeNull();
|
||||
expect(await readLastFullCycleAt('beta')).toBeNull();
|
||||
}, 60_000);
|
||||
|
||||
|
||||
@@ -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);
|
||||
});
|
||||
});
|
||||
Reference in New Issue
Block a user