mirror of
https://github.com/garrytan/gbrain.git
synced 2026-08-17 10:22:34 +00:00
Compare commits
3
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
52fffc7ecc | ||
|
|
039b97df36 | ||
|
|
2bb3424863 |
@@ -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"
|
||||
|
||||
|
||||
+17
-85
@@ -54,7 +54,7 @@ export function bigintToStringReplacer(_key: string, value: unknown): unknown {
|
||||
}
|
||||
|
||||
// CLI-only commands that bypass the operation layer
|
||||
export const CLI_ONLY = new Set(['init', 'reinit-pglite', 'upgrade', 'post-upgrade', 'check-update', 'integrations', 'publish', 'check-backlinks', 'lint', 'report', 'import', 'export', 'files', 'embed', 'serve', 'call', 'config', 'doctor', 'migrate', 'eval', 'sync', 'extract', 'extract-conversation-facts', 'enrich', 'features', 'autopilot', 'graph-query', 'jobs', 'agent', 'apply-migrations', 'skillpack-check', 'skillpack', 'resolvers', 'integrity', 'repair-jsonb', 'orphans', 'sources', 'mounts', 'dream', 'check-resolvable', 'routing-eval', 'skillify', 'smoke-test', 'providers', 'storage', 'repos', 'code-def', 'code-refs', 'reindex', 'reindex-code', 'reindex-frontmatter', 'code-callers', 'code-callees', 'reconcile-links', 'frontmatter', 'auth', 'friction', 'claw-test', 'book-mirror', 'takes', 'think', 'salience', 'anomalies', 'calibration', 'transcripts', 'models', 'remote', 'recall', 'forget', 'edges-backfill', 'cache', 'ze-switch', 'founder', 'brainstorm', 'lsd', 'schema', 'capture', 'onboard', 'conversation-parser', 'status', 'connect', 'skillopt', 'quarantine', 'self-upgrade', 'advisor', 'watch', 'reindex-search-vector']);
|
||||
export const CLI_ONLY = new Set(['init', 'reinit-pglite', 'upgrade', 'post-upgrade', 'check-update', 'integrations', 'publish', 'check-backlinks', 'lint', 'report', 'import', 'export', 'files', 'embed', 'serve', 'call', 'config', 'doctor', 'migrate', 'eval', 'sync', 'extract', 'extract-conversation-facts', 'enrich', 'features', 'autopilot', 'graph-query', 'jobs', 'agent', 'apply-migrations', 'skillpack-check', 'skillpack', 'resolvers', 'integrity', 'repair-jsonb', 'orphans', 'sources', 'mounts', 'dream', 'check-resolvable', 'routing-eval', 'skillify', 'smoke-test', 'providers', 'storage', 'repos', 'code-def', 'code-refs', 'reindex', 'reindex-code', 'reindex-frontmatter', 'code-callers', 'code-callees', 'reconcile-links', 'frontmatter', 'auth', 'friction', 'claw-test', 'book-mirror', 'takes', 'think', 'salience', 'anomalies', 'calibration', 'transcripts', 'models', 'remote', 'recall', 'forget', 'edges-backfill', 'facts', 'cache', 'ze-switch', 'founder', 'brainstorm', 'lsd', 'schema', 'capture', 'onboard', 'conversation-parser', 'status', 'connect', 'skillopt', 'quarantine', 'self-upgrade', 'advisor', 'watch', 'reindex-search-vector']);
|
||||
// CLI-only commands whose handlers print their own --help text. These are
|
||||
// excluded from the generic short-circuit so detailed per-command and
|
||||
// per-subcommand usage stays reachable.
|
||||
@@ -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);
|
||||
@@ -1066,6 +991,8 @@ const THIN_CLIENT_REFUSED_COMMANDS = new Set([
|
||||
// hint pointing at the routable MCP tools; per-subcommand splits are
|
||||
// a v0.31.x follow-up TODO.
|
||||
'takes', 'sources',
|
||||
// #1867: fence-backfill edits local .md fences + stamps the local DB.
|
||||
'facts',
|
||||
// v0.32 thin-client routing audit (Codex round 2 findings #2, #4):
|
||||
// - `pages` purge-deleted is admin+localOnly (operations.ts:856-864)
|
||||
// - `files` list / file_url MCP ops are localOnly (operations.ts:1769-1879)
|
||||
@@ -1101,6 +1028,7 @@ const THIN_CLIENT_REFUSE_HINTS: Record<string, string> = {
|
||||
migrate: "migrate runs on the host's local engine. Run on the host machine.",
|
||||
'apply-migrations': 'schema migrations run on the host. SSH and run there.',
|
||||
'repair-jsonb': 'repair-jsonb operates on the local DB only.',
|
||||
facts: 'facts fence-backfill edits local entity-page fences. Run on the host machine.',
|
||||
integrity: 'integrity scans local files. Run on the host machine.',
|
||||
serve: 'serve starts a server. Run on the host, not the thin client.',
|
||||
dream: 'dream runs the autopilot cycle on the host. `gbrain remote ping` queues one. (Native `gbrain dream` thin-client routing planned for v0.31.2.)',
|
||||
@@ -1930,6 +1858,13 @@ async function handleCliOnly(command: string, args: string[]) {
|
||||
await runEdgesBackfill(engine, args);
|
||||
break;
|
||||
}
|
||||
case 'facts': {
|
||||
// #1867 — re-runnable fence-backfill for row_num-NULL legacy fact
|
||||
// rows (idempotent v0_32_2 phase B, exposed as an operator command).
|
||||
const { runFactsCommand } = await import('./commands/facts.ts');
|
||||
await runFactsCommand(engine, args);
|
||||
break;
|
||||
}
|
||||
case 'whoknows': {
|
||||
// v0.33 (Issue #?): expertise + relationship-proximity routing.
|
||||
// MCP op `find_experts` (read-scoped) backs the same code path; CLI
|
||||
@@ -2328,10 +2263,6 @@ 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)`);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -2414,6 +2345,7 @@ TOOLS
|
||||
check-backlinks <check|fix> [dir] Find/fix missing back-links across brain
|
||||
lint <dir|file> [--fix] Catch LLM artifacts, placeholder dates, bad frontmatter
|
||||
orphans [--json] [--count] Find pages with no inbound wikilinks
|
||||
facts fence-backfill [--dry-run] Fence legacy fact rows (row_num NULL) onto entity pages
|
||||
salience [--days N] [--kind P] v0.29: pages ranked by emotional + activity salience
|
||||
anomalies [--since D] [--sigma N] v0.29: cohort-based statistical anomalies (tag, type)
|
||||
transcripts recent [--days N] v0.29: recent raw .txt transcripts (local-only)
|
||||
|
||||
@@ -0,0 +1,48 @@
|
||||
/**
|
||||
* gbrain facts — fact-store maintenance surface (#1867).
|
||||
*
|
||||
* `fence-backfill` re-runs the v0_32_2 fence-backfill phase on demand.
|
||||
* Remote `extract_facts` deposits that predate the fence-write backstop
|
||||
* (and any legacy DB-only insert) leave `row_num IS NULL` rows that the
|
||||
* cycle extract_facts guard refuses to reconcile past — previously the
|
||||
* only remedy was the one-shot v0_32_2 migration, which the ledger marks
|
||||
* complete and never re-runs. The phase is idempotent (only touches
|
||||
* `row_num IS NULL` rows), so exposing it as a command is safe to re-run
|
||||
* any time the backlog reappears.
|
||||
*/
|
||||
import type { BrainEngine } from '../core/engine.ts';
|
||||
import { setCliExitVerdict } from '../core/cli-force-exit.ts';
|
||||
import { phaseBFenceFacts } from './migrations/v0_32_2.ts';
|
||||
|
||||
function printHelp(): void {
|
||||
process.stderr.write(
|
||||
`Usage: gbrain facts fence-backfill [--dry-run]\n\n` +
|
||||
`Fence-backfill: appends every legacy fact row (row_num IS NULL) to its\n` +
|
||||
`entity page's \`## Facts\` fence and stamps row_num + source_markdown_slug\n` +
|
||||
`back onto the DB row. Idempotent — re-runs only pick up rows still\n` +
|
||||
`missing a fence assignment. Clears the backlog that makes the cycle's\n` +
|
||||
`extract_facts phase skip fence→DB reconciliation.\n\n` +
|
||||
` --dry-run report what would be fenced; no FS or DB writes\n`,
|
||||
);
|
||||
}
|
||||
|
||||
export async function runFactsCommand(engine: BrainEngine, args: string[]): Promise<void> {
|
||||
const sub = args[0];
|
||||
if (!sub || sub === '--help' || sub === '-h') {
|
||||
printHelp();
|
||||
return;
|
||||
}
|
||||
if (sub !== 'fence-backfill') {
|
||||
process.stderr.write(`Unknown facts subcommand: ${sub}\n`);
|
||||
printHelp();
|
||||
setCliExitVerdict(1);
|
||||
return;
|
||||
}
|
||||
|
||||
const dryRun = args.includes('--dry-run');
|
||||
const result = await phaseBFenceFacts(engine, { dryRun });
|
||||
process.stderr.write(
|
||||
`fence-backfill: ${result.status}${result.detail ? ` — ${result.detail}` : ''}\n`,
|
||||
);
|
||||
if (result.status === 'failed') setCliExitVerdict(1);
|
||||
}
|
||||
@@ -39,6 +39,7 @@ import type { BrainEngine } from '../../core/engine.ts';
|
||||
import { loadConfig, toEngineConfig } from '../../core/config.ts';
|
||||
import { createEngine } from '../../core/engine-factory.ts';
|
||||
import { upsertFactRow, parseFactsFence } from '../../core/facts-fence.ts';
|
||||
import { resolvePageFilePath } from '../../core/markdown.ts';
|
||||
|
||||
let testEngineOverride: BrainEngine | null = null;
|
||||
export function __setTestEngineOverride(engine: BrainEngine | null): void {
|
||||
@@ -148,9 +149,16 @@ function isLocalPathDirty(localPath: string): boolean {
|
||||
}
|
||||
}
|
||||
|
||||
async function phaseBFenceFacts(
|
||||
/**
|
||||
* Exported (not just via `__testing`) because `gbrain facts fence-backfill`
|
||||
* (#1867) re-runs this phase on demand: remote `extract_facts` deposits that
|
||||
* predate the fence-write backstop leave row_num-NULL rows the cycle guard
|
||||
* refuses to reconcile past. The phase is idempotent (only touches
|
||||
* `row_num IS NULL` rows), so re-running is always safe.
|
||||
*/
|
||||
export async function phaseBFenceFacts(
|
||||
engine: BrainEngine | null,
|
||||
opts: OrchestratorOpts,
|
||||
opts: Pick<OrchestratorOpts, 'dryRun'>,
|
||||
): Promise<OrchestratorPhaseResult> {
|
||||
if (opts.dryRun) {
|
||||
// Dry-run: report what WOULD happen without touching FS or DB.
|
||||
@@ -238,7 +246,11 @@ async function phaseBFenceFacts(
|
||||
for (const [key, group] of groups) {
|
||||
const [sourceId, entitySlug] = key.split('\0');
|
||||
const localPath = localPathById.get(sourceId)!;
|
||||
const filePath = join(localPath, `${entitySlug}.md`);
|
||||
// resolvePageFilePath, NOT a bare join — non-default sources fence
|
||||
// into `<local_path>/.sources/<id>/<slug>.md`, the same path the
|
||||
// fence-write backstop and put_page write-through compute. A bare
|
||||
// join here diverges fence and DB for non-default sources (#2044).
|
||||
const filePath = resolvePageFilePath(localPath, entitySlug, sourceId);
|
||||
const tmpPath = `${filePath}.tmp`;
|
||||
|
||||
try {
|
||||
@@ -269,6 +281,21 @@ async function phaseBFenceFacts(
|
||||
const existingFence = parseFactsFence(body);
|
||||
const existingKeySet = new Set(existingFence.facts.map(f => `${f.claim}\0${f.source ?? ''}`));
|
||||
|
||||
// Seed appended row_nums from MAX(fence max, DB max) — same #2044
|
||||
// divergence guard as writeFactsToFence. When the fence at the
|
||||
// resolved path is missing/behind but the DB already holds stamped
|
||||
// rows for this slug (legacy wrong-path fence writes), fence-max+1
|
||||
// collides with idx_facts_fence_key on the post-rename UPDATE,
|
||||
// failing the page and leaving fence and DB disagreeing.
|
||||
const dbMaxRows = await engine.executeRaw<{ max: number | string | null }>(
|
||||
`SELECT MAX(row_num) AS max FROM facts
|
||||
WHERE source_id = $1 AND source_markdown_slug = $2`,
|
||||
[sourceId, entitySlug],
|
||||
);
|
||||
const dbMaxRowNum = Number(dbMaxRows[0]?.max ?? 0) || 0;
|
||||
const fenceMaxRowNum = existingFence.facts.reduce((m, f) => Math.max(m, f.rowNum), 0);
|
||||
let nextRowNum = Math.max(fenceMaxRowNum, dbMaxRowNum) + 1;
|
||||
|
||||
const assignments: Array<{ id: string; row_num: number }> = [];
|
||||
for (const row of group) {
|
||||
const key = `${row.fact}\0${row.source ?? ''}`;
|
||||
@@ -291,6 +318,7 @@ async function phaseBFenceFacts(
|
||||
.toISOString().slice(0, 10)
|
||||
: undefined;
|
||||
const { body: updated, rowNum } = upsertFactRow(body, {
|
||||
rowNum: nextRowNum++,
|
||||
claim: row.fact,
|
||||
kind: row.kind,
|
||||
confidence: row.confidence,
|
||||
@@ -381,7 +409,7 @@ async function phaseCVerify(
|
||||
for (const g of groups) {
|
||||
const localPath = localPathById.get(g.source_id);
|
||||
if (!localPath) continue;
|
||||
const filePath = join(localPath, `${g.source_markdown_slug}.md`);
|
||||
const filePath = resolvePageFilePath(localPath, g.source_markdown_slug, g.source_id);
|
||||
if (!existsSync(filePath)) {
|
||||
mismatches.push(`${g.source_markdown_slug} (file missing)`);
|
||||
continue;
|
||||
|
||||
@@ -176,9 +176,11 @@ export async function runExtractFacts(
|
||||
if (legacyCount > 0) {
|
||||
result.guardTriggered = true;
|
||||
result.warnings.push(
|
||||
`extract_facts: ${legacyCount} legacy v0.31 fact rows pending fence backfill. ` +
|
||||
`Run \`gbrain apply-migrations --yes\` to complete v0_32_2 before this phase ` +
|
||||
`can safely reconcile fence → DB.`,
|
||||
`extract_facts: ${legacyCount} legacy fact rows pending fence backfill ` +
|
||||
`(row_num IS NULL — v0.31 rows or remote extract_facts deposits that ` +
|
||||
`predate the fence backstop). Run \`gbrain facts fence-backfill\` ` +
|
||||
`(idempotent, re-runnable) before this phase can safely reconcile ` +
|
||||
`fence → DB.`,
|
||||
);
|
||||
return result;
|
||||
}
|
||||
|
||||
+7
-6
@@ -1739,13 +1739,14 @@ export interface BrainEngine {
|
||||
* single-row supersede flow because fence reconciliation is the canonical
|
||||
* source-of-truth direction, not the consolidator path.
|
||||
*
|
||||
* Insertion is atomic per call: all rows commit in a single transaction
|
||||
* or none commit (the transaction rolls back on any constraint
|
||||
* violation, e.g. the v51 partial UNIQUE index on
|
||||
* `(source_id, source_markdown_slug, row_num)`).
|
||||
* Insertion runs in a single transaction. A collision on the v51
|
||||
* partial UNIQUE index `(source_id, source_markdown_slug, row_num)`
|
||||
* skips ONLY that row (ON CONFLICT DO NOTHING, #2044) — the rest of
|
||||
* the batch still commits, so a redundant deposit against an
|
||||
* already-indexed fence row is idempotent instead of a hard failure.
|
||||
*
|
||||
* Returns the inserted ids in input-order so callers can correlate
|
||||
* fence-row → DB-id without a separate lookup.
|
||||
* Returns the inserted ids in input-order (colliding rows omitted) so
|
||||
* callers can correlate fence-row → DB-id without a separate lookup.
|
||||
*/
|
||||
insertFacts(
|
||||
rows: Array<NewFact & { row_num: number; source_markdown_slug: string }>,
|
||||
|
||||
@@ -218,11 +218,27 @@ export async function writeFactsToFence(
|
||||
}
|
||||
|
||||
// 2. Upsert each fact onto the fence in input order. row_num
|
||||
// monotonically increases (max-existing + 1 per call, append-only).
|
||||
// monotonically increases, append-only, seeded from the MAX of
|
||||
// the fence and the DB index (#2044): when fence and DB have
|
||||
// diverged (e.g. legacy writes that stamped DB rows against a
|
||||
// fence at a path this code no longer reads), fence-max+1 can
|
||||
// collide with an existing DB row_num, tripping
|
||||
// idx_facts_fence_key and rolling back the whole batch.
|
||||
const dbMaxRows = await engine.executeRaw<{ max: number | string | null }>(
|
||||
`SELECT MAX(row_num) AS max FROM facts
|
||||
WHERE source_id = $1 AND source_markdown_slug = $2`,
|
||||
[target.sourceId, target.slug],
|
||||
);
|
||||
const dbMaxRowNum = Number(dbMaxRows[0]?.max ?? 0) || 0;
|
||||
const fenceMaxRowNum = parseFactsFence(body).facts
|
||||
.reduce((m, f) => Math.max(m, f.rowNum), 0);
|
||||
let nextRowNum = Math.max(fenceMaxRowNum, dbMaxRowNum) + 1;
|
||||
|
||||
const assignedRowNums: number[] = [];
|
||||
for (const f of facts) {
|
||||
const validFromStr = (f.validFrom ?? new Date()).toISOString().slice(0, 10);
|
||||
const { body: updated, rowNum } = upsertFactRow(body, {
|
||||
rowNum: nextRowNum++,
|
||||
claim: f.fact,
|
||||
kind: (f.kind ?? 'fact') as 'fact' | 'event' | 'preference' | 'commitment' | 'belief',
|
||||
confidence: f.confidence ?? 1.0,
|
||||
|
||||
@@ -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,
|
||||
|
||||
@@ -4102,11 +4102,13 @@ export class PGLiteEngine implements BrainEngine {
|
||||
): Promise<{ inserted: number; ids: number[] }> {
|
||||
if (rows.length === 0) return { inserted: 0, ids: [] };
|
||||
|
||||
// Single transaction so the v51 partial UNIQUE index can roll back the
|
||||
// whole batch on constraint violation. Per-row INSERTs (not multi-row
|
||||
// VALUES) keep the embedding-vs-no-embedding branching readable; batch
|
||||
// sizes are small (5-30 rows per page in practice) so the loop overhead
|
||||
// is negligible vs the embedding compute cost.
|
||||
// Single transaction; per-row INSERTs (not multi-row VALUES) keep the
|
||||
// embedding-vs-no-embedding branching readable; batch sizes are small
|
||||
// (5-30 rows per page in practice) so the loop overhead is negligible
|
||||
// vs the embedding compute cost. #2044: ON CONFLICT DO NOTHING on the
|
||||
// v51 partial UNIQUE index makes a residual fence/DB row_num collision
|
||||
// skip that row instead of rolling back the whole batch (parity with
|
||||
// postgres-engine.ts).
|
||||
const ids = await this.db.transaction(async (tx) => {
|
||||
const out: number[] = [];
|
||||
for (const input of rows) {
|
||||
@@ -4149,7 +4151,11 @@ export class PGLiteEngine implements BrainEngine {
|
||||
$14, $15,
|
||||
$16, $17, $18, $19,
|
||||
$20
|
||||
) RETURNING id`
|
||||
)
|
||||
ON CONFLICT (source_id, source_markdown_slug, row_num)
|
||||
WHERE row_num IS NOT NULL
|
||||
DO NOTHING
|
||||
RETURNING id`
|
||||
: `INSERT INTO facts (
|
||||
source_id, entity_slug, fact, kind, visibility, notability, context,
|
||||
valid_from, valid_until, source, source_session, confidence,
|
||||
@@ -4163,12 +4169,16 @@ export class PGLiteEngine implements BrainEngine {
|
||||
$15, $16,
|
||||
$17, $18, $19, $20,
|
||||
$21
|
||||
) RETURNING id`,
|
||||
)
|
||||
ON CONFLICT (source_id, source_markdown_slug, row_num)
|
||||
WHERE row_num IS NOT NULL
|
||||
DO NOTHING
|
||||
RETURNING id`,
|
||||
embedStr === null
|
||||
? [ctx.source_id, entitySlug, input.fact, kind, visibility, notability, context, validFrom, validUntil, input.source, sourceSession, confidence, embeddedAt, input.row_num, input.source_markdown_slug, claimMetric, claimValue, claimUnit, claimPeriod, eventType]
|
||||
: [ctx.source_id, entitySlug, input.fact, kind, visibility, notability, context, validFrom, validUntil, input.source, sourceSession, confidence, embedStr, embeddedAt, input.row_num, input.source_markdown_slug, claimMetric, claimValue, claimUnit, claimPeriod, eventType],
|
||||
);
|
||||
out.push(ins.rows[0].id);
|
||||
if (ins.rows[0]) out.push(ins.rows[0].id);
|
||||
}
|
||||
return out;
|
||||
});
|
||||
|
||||
@@ -4302,10 +4302,12 @@ export class PostgresEngine implements BrainEngine {
|
||||
// ONCE per process so the cast matches the actual column type
|
||||
// (halfvec vs vector). The probe is cached after first call.
|
||||
const castSuffix = await this.resolveFactsEmbeddingCast();
|
||||
// Single transaction so the v51 partial UNIQUE index can roll back
|
||||
// the whole batch on constraint violation. Per-row INSERTs (not
|
||||
// multi-row VALUES) keep the embedding-vs-no-embedding branching
|
||||
// readable; batch sizes are small (5-30 rows per page in practice).
|
||||
// Single transaction; per-row INSERTs (not multi-row VALUES) keep the
|
||||
// embedding-vs-no-embedding branching readable; batch sizes are small
|
||||
// (5-30 rows per page in practice). #2044: ON CONFLICT DO NOTHING on
|
||||
// the v51 partial UNIQUE index makes a residual fence/DB row_num
|
||||
// collision skip that row instead of rolling back the whole batch —
|
||||
// the fence stays system-of-record and reconciliation catches up.
|
||||
// No supersede flow in this path — fence reconciliation is the
|
||||
// canonical source-of-truth direction, not the consolidator path.
|
||||
const ids = await sql.begin(async (tx) => {
|
||||
@@ -4346,9 +4348,13 @@ export class PostgresEngine implements BrainEngine {
|
||||
${input.row_num}, ${input.source_markdown_slug},
|
||||
${claimMetric}, ${claimValue}, ${claimUnit}, ${claimPeriod},
|
||||
${eventType}
|
||||
) RETURNING id
|
||||
)
|
||||
ON CONFLICT (source_id, source_markdown_slug, row_num)
|
||||
WHERE row_num IS NOT NULL
|
||||
DO NOTHING
|
||||
RETURNING id
|
||||
`;
|
||||
out.push(Number(ins[0].id));
|
||||
if (ins[0]) out.push(Number(ins[0].id));
|
||||
}
|
||||
return out;
|
||||
});
|
||||
|
||||
@@ -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,
|
||||
|
||||
@@ -304,7 +304,9 @@ describe('runExtractFacts — empty-fence guard (Codex R2-#7)', () => {
|
||||
expect(r.legacyRowsPending).toBe(1);
|
||||
expect(r.factsInserted).toBe(0);
|
||||
expect(r.factsDeleted).toBe(0);
|
||||
expect(r.warnings.some(w => w.includes('apply-migrations'))).toBe(true);
|
||||
// #1867: the remedy hint points at the re-runnable backfill command,
|
||||
// not the one-shot v0_32_2 migration (which the ledger never re-runs).
|
||||
expect(r.warnings.some(w => w.includes('gbrain facts fence-backfill'))).toBe(true);
|
||||
|
||||
// Legacy row was NOT touched.
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
|
||||
@@ -0,0 +1,133 @@
|
||||
/**
|
||||
* #1867 — `gbrain facts fence-backfill` command tests.
|
||||
*
|
||||
* The command re-runs the (idempotent) v0_32_2 phase B on demand so
|
||||
* row_num-NULL backlogs — remote extract_facts deposits that predate
|
||||
* the fence-write backstop — can be cleared without re-running the
|
||||
* one-shot migration. Real PGLite + real tempdir filesystem.
|
||||
*/
|
||||
|
||||
import { describe, test, expect, beforeAll, afterAll, beforeEach } from 'bun:test';
|
||||
import { mkdtempSync, rmSync, existsSync, readFileSync } from 'node:fs';
|
||||
import { tmpdir } from 'node:os';
|
||||
import { join } from 'node:path';
|
||||
|
||||
import { PGLiteEngine } from '../src/core/pglite-engine.ts';
|
||||
import { runFactsCommand } from '../src/commands/facts.ts';
|
||||
import { phaseBFenceFacts } from '../src/commands/migrations/v0_32_2.ts';
|
||||
|
||||
let engine: PGLiteEngine;
|
||||
let brainDir: string;
|
||||
|
||||
beforeAll(async () => {
|
||||
engine = new PGLiteEngine();
|
||||
await engine.connect({});
|
||||
await engine.initSchema();
|
||||
});
|
||||
|
||||
afterAll(async () => {
|
||||
await engine.disconnect();
|
||||
try {
|
||||
if (brainDir) rmSync(brainDir, { recursive: true, force: true });
|
||||
} catch { /* best-effort */ }
|
||||
});
|
||||
|
||||
beforeEach(async () => {
|
||||
brainDir = mkdtempSync(join(tmpdir(), 'facts-backfill-cmd-test-'));
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
await (engine as any).db.query('DELETE FROM facts');
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
await (engine as any).db.query(
|
||||
`UPDATE sources SET local_path = $1 WHERE id = 'default'`,
|
||||
[brainDir],
|
||||
);
|
||||
});
|
||||
|
||||
async function seedLegacyFact(fact: string): Promise<void> {
|
||||
// The row_num-NULL shape a remote extract_facts deposit leaves behind
|
||||
// when it lands via the legacy DB-only path.
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
await (engine as any).db.query(
|
||||
`INSERT INTO facts (source_id, entity_slug, fact, kind, visibility, notability,
|
||||
valid_from, source, confidence)
|
||||
VALUES ('default', 'people/alice', $1, 'fact', 'private', 'medium',
|
||||
now(), 'mcp:extract_facts', 1.0)`,
|
||||
[fact],
|
||||
);
|
||||
}
|
||||
|
||||
describe('gbrain facts fence-backfill', () => {
|
||||
test('fences row_num-NULL rows and stamps the DB', async () => {
|
||||
await seedLegacyFact('Deposited remotely');
|
||||
|
||||
await runFactsCommand(engine, ['fence-backfill']);
|
||||
|
||||
// The fence exists on disk with the claim.
|
||||
const filePath = join(brainDir, 'people/alice.md');
|
||||
expect(existsSync(filePath)).toBe(true);
|
||||
expect(readFileSync(filePath, 'utf-8')).toContain('Deposited remotely');
|
||||
|
||||
// The backlog is cleared: no row_num-NULL rows remain.
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
const rows = await (engine as any).db.query(
|
||||
'SELECT row_num, source_markdown_slug FROM facts',
|
||||
);
|
||||
expect(rows.rows).toHaveLength(1);
|
||||
expect(rows.rows[0].row_num).toBe(1);
|
||||
expect(rows.rows[0].source_markdown_slug).toBe('people/alice');
|
||||
});
|
||||
|
||||
test('re-run is a no-op (idempotent)', async () => {
|
||||
await seedLegacyFact('Deposited remotely');
|
||||
await runFactsCommand(engine, ['fence-backfill']);
|
||||
await runFactsCommand(engine, ['fence-backfill']);
|
||||
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
const rows = await (engine as any).db.query('SELECT id FROM facts');
|
||||
expect(rows.rows).toHaveLength(1);
|
||||
const body = readFileSync(join(brainDir, 'people/alice.md'), 'utf-8');
|
||||
expect(body.match(/Deposited remotely/g)).toHaveLength(1);
|
||||
});
|
||||
|
||||
test('--dry-run reports without writing', async () => {
|
||||
await seedLegacyFact('Deposited remotely');
|
||||
await runFactsCommand(engine, ['fence-backfill', '--dry-run']);
|
||||
|
||||
expect(existsSync(join(brainDir, 'people/alice.md'))).toBe(false);
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
const rows = await (engine as any).db.query(
|
||||
'SELECT row_num FROM facts',
|
||||
);
|
||||
expect(rows.rows[0].row_num).toBeNull();
|
||||
});
|
||||
|
||||
test('diverged page: appends past the DB row_num max instead of colliding (#2044 class)', async () => {
|
||||
// The #2044 divergence shape the backfill must survive: the DB already
|
||||
// holds stamped rows 1..3 for the slug (legacy wrong-path fence write),
|
||||
// but the fence at the resolved path is missing. Fence-max+1 (= 1) would
|
||||
// collide with the stamped rows on the post-rename UPDATE, failing the
|
||||
// page and leaving the renamed fence disagreeing with the DB.
|
||||
for (let n = 1; n <= 3; n++) {
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
await (engine as any).db.query(
|
||||
`INSERT INTO facts (source_id, entity_slug, fact, kind, visibility, notability,
|
||||
valid_from, source, confidence, row_num, source_markdown_slug)
|
||||
VALUES ('default', 'people/alice', $1, 'fact', 'private', 'medium',
|
||||
now(), 'mcp:extract_facts', 1.0, $2, 'people/alice')`,
|
||||
[`stamped ${n}`, n],
|
||||
);
|
||||
}
|
||||
await seedLegacyFact('Deposited remotely');
|
||||
|
||||
const result = await phaseBFenceFacts(engine, { dryRun: false });
|
||||
expect(result.status).toBe('complete');
|
||||
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
const rows = await (engine as any).db.query(
|
||||
`SELECT row_num FROM facts WHERE fact = 'Deposited remotely'`,
|
||||
);
|
||||
expect(rows.rows[0].row_num).toBe(4);
|
||||
const body = readFileSync(join(brainDir, 'people/alice.md'), 'utf-8');
|
||||
expect(body).toContain('| 4 | Deposited remotely |');
|
||||
});
|
||||
});
|
||||
@@ -292,6 +292,49 @@ describe('lookupSourceLocalPath', () => {
|
||||
});
|
||||
});
|
||||
|
||||
describe('writeFactsToFence — fence/DB divergence (#2044)', () => {
|
||||
test('seeds row_num past the DB max when the fence lags the DB', async () => {
|
||||
// Simulate the divergence class from #2044: DB rows were stamped with
|
||||
// row_nums against a fence written at a path this code no longer reads
|
||||
// (e.g. the pre-"Local patch 2026-06-11" wrong-path writes). The page
|
||||
// on disk has NO fence, but the DB already holds row_num 1..3 for the
|
||||
// slug. Pre-fix, the next deposit re-assigned row_num=1 from fence
|
||||
// text alone and the whole insertFacts batch failed on
|
||||
// idx_facts_fence_key.
|
||||
for (let n = 1; n <= 3; n++) {
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
await (engine as any).db.query(
|
||||
`INSERT INTO facts (source_id, entity_slug, fact, kind, visibility, notability,
|
||||
valid_from, source, confidence, row_num, source_markdown_slug)
|
||||
VALUES ('default', 'people/dana', $1, 'fact', 'private', 'medium',
|
||||
now(), 'mcp:extract_facts', 1.0, $2, 'people/dana')`,
|
||||
[`old claim ${n}`, n],
|
||||
);
|
||||
}
|
||||
|
||||
const result = await writeFactsToFence(
|
||||
engine,
|
||||
{ sourceId: 'default', localPath: brainDir, slug: 'people/dana' },
|
||||
[baseInput({ fact: 'second deposit' })],
|
||||
);
|
||||
|
||||
expect(result.fenceWriteFailed).toBeUndefined();
|
||||
expect(result.inserted).toBe(1);
|
||||
|
||||
// The new row landed PAST the DB max, not at fence-max+1 (= 1).
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
const rows = await (engine as any).db.query(
|
||||
'SELECT row_num FROM facts WHERE id = $1',
|
||||
[result.ids[0]],
|
||||
);
|
||||
expect(rows.rows[0].row_num).toBe(4);
|
||||
|
||||
// And the on-disk fence carries the same row_num — fence and DB agree.
|
||||
const body = readFileSync(join(brainDir, 'people/dana.md'), 'utf-8');
|
||||
expect(body).toContain('| 4 | second deposit |');
|
||||
});
|
||||
});
|
||||
|
||||
// Cleanup any leftover tempdirs after the whole suite.
|
||||
afterAll(() => {
|
||||
// No-op: each test cleaned up via the beforeEach; this is a safety net.
|
||||
|
||||
@@ -5,7 +5,7 @@
|
||||
* - Batch insert N rows persists row_num + source_markdown_slug
|
||||
* - Empty batch is a no-op
|
||||
* - Returns ids in input-order
|
||||
* - v51 partial UNIQUE index rolls back the whole batch on a collision
|
||||
* - v51 partial UNIQUE collision skips only the colliding row (#2044)
|
||||
* - deleteFactsForPage scopes by (source_id, source_markdown_slug);
|
||||
* never touches other pages or pre-v51 NULL-source_markdown_slug rows
|
||||
* - deleteFactsForPage on an empty page returns deleted:0 (idempotent)
|
||||
@@ -135,30 +135,29 @@ describe('engine.insertFacts — batch insert', () => {
|
||||
});
|
||||
});
|
||||
|
||||
test('v51 partial UNIQUE index rolls back the whole batch on collision', async () => {
|
||||
test('v51 partial UNIQUE collision skips ONLY the colliding row (#2044)', async () => {
|
||||
// Seed row #1 first.
|
||||
await engine.insertFacts([fixtureFact(1, { fact: 'seeded' })], { source_id: 'default' });
|
||||
|
||||
// Now try to batch-insert rows that include a colliding row_num=1.
|
||||
let threw = false;
|
||||
try {
|
||||
await engine.insertFacts(
|
||||
[
|
||||
fixtureFact(2, { fact: 'second' }),
|
||||
fixtureFact(1, { fact: 'collides' }), // row_num=1 on same (source_id, source_markdown_slug)
|
||||
fixtureFact(3, { fact: 'third' }),
|
||||
],
|
||||
{ source_id: 'default' },
|
||||
);
|
||||
} catch {
|
||||
threw = true;
|
||||
}
|
||||
expect(threw).toBe(true);
|
||||
// Batch-insert rows that include a colliding row_num=1. Pre-#2044 this
|
||||
// threw and rolled back the whole batch, making a second remote
|
||||
// extract_facts deposit to an already-fenced page a hard failure. Now
|
||||
// ON CONFLICT DO NOTHING skips the colliding row and keeps the rest.
|
||||
const result = await engine.insertFacts(
|
||||
[
|
||||
fixtureFact(2, { fact: 'second' }),
|
||||
fixtureFact(1, { fact: 'collides' }), // row_num=1 on same (source_id, source_markdown_slug)
|
||||
fixtureFact(3, { fact: 'third' }),
|
||||
],
|
||||
{ source_id: 'default' },
|
||||
);
|
||||
expect(result.inserted).toBe(2);
|
||||
expect(result.ids).toHaveLength(2);
|
||||
|
||||
// Verify the transaction rolled back — only the seeded row should remain.
|
||||
// The seeded row survives untouched; the colliding claim is skipped.
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
const rows = await (engine as any).db.query('SELECT fact FROM facts ORDER BY id');
|
||||
expect(rows.rows.map((r: { fact: string }) => r.fact)).toEqual(['seeded']);
|
||||
expect(rows.rows.map((r: { fact: string }) => r.fact)).toEqual(['seeded', 'second', 'third']);
|
||||
});
|
||||
|
||||
test('different source_markdown_slug values DO NOT collide on the same row_num', async () => {
|
||||
|
||||
@@ -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