mirror of
https://github.com/garrytan/gbrain.git
synced 2026-08-16 09:52:22 +00:00
Compare commits
2
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
ba6b5d4690 | ||
|
|
827c1619ac |
@@ -3,7 +3,11 @@
|
||||
*
|
||||
* Usage:
|
||||
* gbrain migrate --to supabase [--url <connection_string>]
|
||||
* (--url is persisted to config.json, mode 0600, so the migrated brain
|
||||
* works without env — #1271)
|
||||
* gbrain migrate --to pglite [--path <db_path>]
|
||||
* (an explicit --path destination is bootstrapped with its own
|
||||
* <path>/.gbrain/config.json so GBRAIN_HOME=<path> just works — #1271)
|
||||
* gbrain migrate --to <engine> --force (overwrite non-empty target)
|
||||
*/
|
||||
|
||||
@@ -11,9 +15,9 @@ import { createEngine } from '../core/engine-factory.ts';
|
||||
import { loadConfig, saveConfig, toEngineConfig, gbrainPath, effectiveEnvDatabaseUrl, type GBrainConfig } from '../core/config.ts';
|
||||
import type { BrainEngine } from '../core/engine.ts';
|
||||
import type { EngineConfig } from '../core/types.ts';
|
||||
import { writeFileSync, readFileSync, existsSync, unlinkSync } from 'fs';
|
||||
import { writeFileSync, readFileSync, existsSync, unlinkSync, mkdirSync, chmodSync } from 'fs';
|
||||
import { createHash } from 'crypto';
|
||||
import { resolve } from 'path';
|
||||
import { resolve, join } from 'path';
|
||||
import { createProgress } from '../core/progress.ts';
|
||||
import { getCliOptions, cliOptsToProgressOptions } from '../core/cli-options.ts';
|
||||
|
||||
@@ -59,6 +63,31 @@ export interface MigrateManifest {
|
||||
started_at: string;
|
||||
}
|
||||
|
||||
/**
|
||||
* #1271 Finding 1: make an explicit `--to pglite --path P` destination usable
|
||||
* as a standalone brain. Writes `P/.gbrain/config.json` (mode 0600, plus a
|
||||
* `*` .gitignore) so `GBRAIN_HOME=P` resolves without a manual `gbrain init`.
|
||||
* Never clobbers an existing config at the destination. Returns the written
|
||||
* config path, or null when skipped.
|
||||
*/
|
||||
export function bootstrapDestinationConfig(dbPath: string): string | null {
|
||||
const abs = resolve(dbPath);
|
||||
const dir = join(abs, '.gbrain');
|
||||
const file = join(dir, 'config.json');
|
||||
if (existsSync(file)) return null;
|
||||
mkdirSync(dir, { recursive: true });
|
||||
const cfg: GBrainConfig = { engine: 'pglite', database_path: abs };
|
||||
writeFileSync(file, JSON.stringify(cfg, null, 2) + '\n', { mode: 0o600 });
|
||||
try { chmodSync(file, 0o600); } catch { /* platform-specific */ }
|
||||
// Same worktree-safety pattern as saveConfig()'s ensureGitignore, scoped
|
||||
// to the destination home. Don't clobber a user-customized .gitignore.
|
||||
const gitignore = join(dir, '.gitignore');
|
||||
if (!existsSync(gitignore)) {
|
||||
writeFileSync(gitignore, '*\n', { mode: 0o600 });
|
||||
}
|
||||
return file;
|
||||
}
|
||||
|
||||
export function migrationTargetId(config: EngineConfig): string {
|
||||
const locator = config.engine === 'postgres'
|
||||
? config.database_url ?? ''
|
||||
@@ -352,6 +381,25 @@ export async function runMigrateEngine(sourceEngine: BrainEngine, args: string[]
|
||||
};
|
||||
saveConfig(newConfig);
|
||||
|
||||
// #1271 Finding 2 (by design, but say it out loud): the connection string
|
||||
// is persisted so the migrated brain works without env. Mode 0600.
|
||||
if (opts.targetEngine === 'postgres' && opts.targetUrl) {
|
||||
console.error('Note: the --url connection string (including credentials) is persisted to config.json (mode 0600).');
|
||||
}
|
||||
|
||||
// #1271 Finding 1: an explicit --path destination doubles as a standalone
|
||||
// GBRAIN_HOME. Best-effort — never fail a completed migration over it.
|
||||
if (opts.targetEngine === 'pglite' && opts.targetPath) {
|
||||
try {
|
||||
const written = bootstrapDestinationConfig(opts.targetPath);
|
||||
if (written) {
|
||||
console.log(`Destination bootstrapped: ${written} (usable via GBRAIN_HOME=${resolve(opts.targetPath)})`);
|
||||
}
|
||||
} catch (e) {
|
||||
console.warn(` WARN could not bootstrap destination config: ${e instanceof Error ? e.message : String(e)}`);
|
||||
}
|
||||
}
|
||||
|
||||
// Clean up
|
||||
clearManifest();
|
||||
|
||||
|
||||
@@ -197,7 +197,7 @@ export interface SyncResult {
|
||||
/** Pages re-embedded during this sync's auto-embed step. 0 if --no-embed or skipped. */
|
||||
embedded: number;
|
||||
pagesAffected: string[];
|
||||
failedFiles?: number; // count of per-file import/sync failures (Bug 9)
|
||||
failedFiles?: number; // count of parse failures (Bug 9)
|
||||
/**
|
||||
* v0.41.13.0 partial-sync fields (only set when status === 'partial').
|
||||
*
|
||||
@@ -3183,7 +3183,7 @@ async function performSyncInner(engine: BrainEngine, opts: SyncOpts): Promise<Sy
|
||||
await clearOpCheckpoint(engine, ckpt.target);
|
||||
};
|
||||
|
||||
// issue #1939 adversarial finding #1: a file that failed to import (open ledger
|
||||
// issue #1939 adversarial finding #1: a file that failed to parse (open ledger
|
||||
// row) and is then deleted/renamed-away never re-enters failedFiles and never
|
||||
// imports, so its row would never clear and would age doctor to a permanent
|
||||
// FAIL. Treat removed paths as resolved so the ledger self-heals.
|
||||
@@ -3215,9 +3215,9 @@ async function performSyncInner(engine: BrainEngine, opts: SyncOpts): Promise<Sy
|
||||
} else {
|
||||
const fileFailCount = failedFiles.filter(f => isSkippablePath(f.path)).length;
|
||||
serr(
|
||||
`\nSync blocked: ${fileFailCount} file(s) failed to import:\n` +
|
||||
`\nSync blocked: ${fileFailCount} file(s) failed to parse:\n` +
|
||||
`${codeBreakdown}\n\n` +
|
||||
`Fix the listed file errors and re-run, or use 'gbrain sync --skip-failed' to ` +
|
||||
`Fix the frontmatter and re-run, or use 'gbrain sync --skip-failed' to ` +
|
||||
`acknowledge and move on. A file that keeps failing auto-skips after ` +
|
||||
`${resolveAutoSkipThreshold()} consecutive syncs.`,
|
||||
);
|
||||
@@ -5355,7 +5355,7 @@ function printSyncResult(result: SyncResult, sink: NodeJS.WriteStream = process.
|
||||
case 'dry_run':
|
||||
break; // already printed in performSync
|
||||
case 'blocked_by_failures':
|
||||
write(`Sync BLOCKED at ${result.toCommit.slice(0, 8)}: ${result.failedFiles ?? 0} file(s) failed to import.`);
|
||||
write(`Sync BLOCKED at ${result.toCommit.slice(0, 8)}: ${result.failedFiles ?? 0} file(s) failed to parse.`);
|
||||
write(` See ~/.gbrain/sync-failures.jsonl for details, or run 'gbrain doctor'.`);
|
||||
write(` Fix the files then re-run 'gbrain sync', or 'gbrain sync --skip-failed' to move on.`);
|
||||
break;
|
||||
|
||||
@@ -1058,16 +1058,6 @@ export class PGLiteEngine implements BrainEngine {
|
||||
RETURNING id, source_id, slug, type, title, compiled_truth, timeline, frontmatter, content_hash, created_at, updated_at, effective_date, effective_date_source, import_filename, source_kind, source_uri, ingested_via, ingested_at`,
|
||||
[sourceId, slug, page.type, pageKind, page.title, page.compiled_truth, page.timeline || '', JSON.stringify(frontmatter), hash, effectiveDate, effectiveDateSource, importFilename, chunkerVersion, sourcePath, sourceKind, sourceUri, ingestedVia, ingestedAt]
|
||||
);
|
||||
// #2189: an INSERT … ON CONFLICT DO UPDATE … RETURNING that yields 0 rows
|
||||
// (e.g. a BEFORE trigger suppressing the write) previously crashed in
|
||||
// rowToPage with an opaque "undefined is not an object (row.deleted_at)".
|
||||
// Throw a diagnosable error naming the row instead. Mirrors postgres-engine.ts.
|
||||
if (!rows[0]) {
|
||||
throw new Error(
|
||||
`putPage: INSERT … RETURNING produced no row for slug='${slug}' source_id='${sourceId}'. ` +
|
||||
`A trigger or rule on the pages table may be suppressing the write.`
|
||||
);
|
||||
}
|
||||
return rowToPage(rows[0] as Record<string, unknown>);
|
||||
}
|
||||
|
||||
|
||||
@@ -1119,16 +1119,6 @@ export class PostgresEngine implements BrainEngine {
|
||||
ingested_at = COALESCE(EXCLUDED.ingested_at, pages.ingested_at)
|
||||
RETURNING id, source_id, slug, type, title, compiled_truth, timeline, frontmatter, content_hash, created_at, updated_at, effective_date, effective_date_source, import_filename, source_kind, source_uri, ingested_via, ingested_at
|
||||
`;
|
||||
// #2189: an INSERT … ON CONFLICT DO UPDATE … RETURNING that yields 0 rows
|
||||
// (e.g. a BEFORE trigger suppressing the write) previously crashed in
|
||||
// rowToPage with an opaque "undefined is not an object (row.deleted_at)".
|
||||
// Throw a diagnosable error naming the row instead. Mirrors pglite-engine.ts.
|
||||
if (!rows[0]) {
|
||||
throw new Error(
|
||||
`putPage: INSERT … RETURNING produced no row for slug='${slug}' source_id='${sourceId}'. ` +
|
||||
`A trigger or rule on the pages table may be suppressing the write.`
|
||||
);
|
||||
}
|
||||
return rowToPage(rows[0]);
|
||||
}
|
||||
|
||||
|
||||
@@ -0,0 +1,40 @@
|
||||
import { describe, expect, test } from 'bun:test';
|
||||
import { mkdtempSync, mkdirSync, readFileSync, statSync, writeFileSync } from 'fs';
|
||||
import { tmpdir } from 'os';
|
||||
import { join, resolve } from 'path';
|
||||
import { bootstrapDestinationConfig } from '../src/commands/migrate-engine.ts';
|
||||
import { loadConfigFileOnly } from '../src/core/config.ts';
|
||||
import { withEnv } from './helpers/with-env.ts';
|
||||
|
||||
describe('migrate --to pglite destination bootstrap (#1271)', () => {
|
||||
test('writes <path>/.gbrain/config.json so GBRAIN_HOME=<path> resolves a brain', async () => {
|
||||
const dest = mkdtempSync(join(tmpdir(), 'gbrain-dest-'));
|
||||
const written = bootstrapDestinationConfig(dest);
|
||||
const file = join(dest, '.gbrain', 'config.json');
|
||||
expect(written).toBe(file);
|
||||
|
||||
const cfg = JSON.parse(readFileSync(file, 'utf-8'));
|
||||
expect(cfg.engine).toBe('pglite');
|
||||
expect(cfg.database_path).toBe(resolve(dest));
|
||||
expect(statSync(file).mode & 0o777).toBe(0o600);
|
||||
// worktree safety: destination home is git-ignored like saveConfig()'s home
|
||||
expect(readFileSync(join(dest, '.gbrain', '.gitignore'), 'utf-8')).toBe('*\n');
|
||||
|
||||
// The exact failure mode from #1271: config resolution under
|
||||
// GBRAIN_HOME=<path> used to find nothing ("No brain configured").
|
||||
await withEnv({ GBRAIN_HOME: dest }, () => {
|
||||
const loaded = loadConfigFileOnly();
|
||||
expect(loaded?.engine).toBe('pglite');
|
||||
expect(loaded?.database_path).toBe(resolve(dest));
|
||||
});
|
||||
});
|
||||
|
||||
test('never clobbers an existing destination config', () => {
|
||||
const dest = mkdtempSync(join(tmpdir(), 'gbrain-dest-'));
|
||||
mkdirSync(join(dest, '.gbrain'), { recursive: true });
|
||||
writeFileSync(join(dest, '.gbrain', 'config.json'), '{"engine":"postgres"}\n');
|
||||
|
||||
expect(bootstrapDestinationConfig(dest)).toBe(null);
|
||||
expect(JSON.parse(readFileSync(join(dest, '.gbrain', 'config.json'), 'utf-8')).engine).toBe('postgres');
|
||||
});
|
||||
});
|
||||
@@ -1,74 +0,0 @@
|
||||
// #2189 regression guard: putPage's INSERT … ON CONFLICT DO UPDATE … RETURNING
|
||||
// can yield 0 rows when brain-local DB state (e.g. a BEFORE INSERT trigger)
|
||||
// suppresses the write. Pre-fix, rowToPage(rows[0]) crashed with the opaque
|
||||
// "undefined is not an object (evaluating 'row.deleted_at')" that failed
|
||||
// ~all files of a code sync. Post-fix, putPage throws a descriptive error
|
||||
// naming the slug + source_id so the failure is diagnosable per-file.
|
||||
//
|
||||
// Same guard lands in postgres-engine.ts (engine-parity invariant); this test
|
||||
// exercises the PGLite side, where the issue was reported.
|
||||
|
||||
import { describe, expect, test, beforeAll, afterAll } from 'bun:test';
|
||||
import { PGLiteEngine } from '../src/core/pglite-engine.ts';
|
||||
|
||||
let engine: PGLiteEngine;
|
||||
|
||||
beforeAll(async () => {
|
||||
engine = new PGLiteEngine();
|
||||
await engine.connect({});
|
||||
await engine.initSchema();
|
||||
// Simulate the reporter's state-dependent failure: a trigger that
|
||||
// suppresses inserts for one slug, making RETURNING produce no row.
|
||||
await engine.executeRaw(`
|
||||
CREATE OR REPLACE FUNCTION suppress_pages_insert() RETURNS trigger AS $$
|
||||
BEGIN
|
||||
IF NEW.slug = 'suppressed-page' THEN RETURN NULL; END IF;
|
||||
RETURN NEW;
|
||||
END;
|
||||
$$ LANGUAGE plpgsql;
|
||||
`);
|
||||
await engine.executeRaw(`
|
||||
CREATE TRIGGER suppress_pages_insert_trg
|
||||
BEFORE INSERT ON pages
|
||||
FOR EACH ROW EXECUTE FUNCTION suppress_pages_insert();
|
||||
`);
|
||||
});
|
||||
|
||||
afterAll(async () => {
|
||||
await engine.executeRaw('DROP TRIGGER IF EXISTS suppress_pages_insert_trg ON pages');
|
||||
await engine.executeRaw('DROP FUNCTION IF EXISTS suppress_pages_insert');
|
||||
await engine.disconnect();
|
||||
});
|
||||
|
||||
describe('putPage RETURNING guard (#2189)', () => {
|
||||
test('0-row RETURNING throws a descriptive error, not row.deleted_at TypeError', async () => {
|
||||
let err: Error | undefined;
|
||||
try {
|
||||
await engine.putPage('suppressed-page', {
|
||||
type: 'code',
|
||||
title: 'Suppressed',
|
||||
compiled_truth: 'x',
|
||||
timeline: '',
|
||||
});
|
||||
} catch (e) {
|
||||
err = e as Error;
|
||||
}
|
||||
expect(err).toBeDefined();
|
||||
expect(err!.message).toContain('putPage');
|
||||
expect(err!.message).toContain("slug='suppressed-page'");
|
||||
expect(err!.message).toContain("source_id='default'");
|
||||
// The pre-fix crash signature must be gone.
|
||||
expect(err!.message).not.toContain('deleted_at');
|
||||
});
|
||||
|
||||
test('unsuppressed slugs still upsert normally with the trigger installed', async () => {
|
||||
const page = await engine.putPage('normal-page', {
|
||||
type: 'concept',
|
||||
title: 'Normal',
|
||||
compiled_truth: 'y',
|
||||
timeline: '',
|
||||
});
|
||||
expect(page.slug).toBe('normal-page');
|
||||
expect(page.source_id).toBe('default');
|
||||
});
|
||||
});
|
||||
@@ -375,31 +375,6 @@ describe('performSync dry-run never writes', () => {
|
||||
expect(messages.some(m => m.includes('git pull failed'))).toBe(false);
|
||||
});
|
||||
|
||||
test('first PGLite code sync imports code files without runtime failures', async () => {
|
||||
const { performSync } = await import('../src/commands/sync.ts');
|
||||
mkdirSync(join(repoPath, 'src'), { recursive: true });
|
||||
writeFileSync(
|
||||
join(repoPath, 'src/example.ts'),
|
||||
'export function add(left: number, right: number) { return left + right; }\n',
|
||||
);
|
||||
execSync('git add -A && git commit -m "add code file"', { cwd: repoPath, stdio: 'pipe' });
|
||||
|
||||
const result = await performSync(engine, {
|
||||
repoPath,
|
||||
noPull: true,
|
||||
noEmbed: true,
|
||||
noExtract: true,
|
||||
strategy: 'code',
|
||||
});
|
||||
|
||||
expect(result.status).toBe('first_sync');
|
||||
expect(result.added).toBe(1);
|
||||
expect(result.failedFiles ?? 0).toBe(0);
|
||||
const page = await engine.getPage('src-example-ts');
|
||||
expect(page?.type).toBe('code');
|
||||
expect(page?.frontmatter).toMatchObject({ file: 'src/example.ts', language: 'typescript' });
|
||||
});
|
||||
|
||||
test('incremental dry-run does NOT write to DB or advance the bookmark', async () => {
|
||||
const { performSync } = await import('../src/commands/sync.ts');
|
||||
// First do a real sync to seed the bookmark.
|
||||
|
||||
Reference in New Issue
Block a user