Compare commits

..
Author SHA1 Message Date
Garry TanandClaude Fable 5 623d683e40 fix(thin-client): keep ambient scope out of get_skill's non-scope source_id param
get_skill's source_id is a mode switch (host catalog vs brain-resident-pack
lookup), not a read-scope filter. Ambient GBRAIN_SOURCE / .gbrain-source
injection would silently reroute 'gbrain skill <name>' on thin clients to
getResidentSkillDetail. Exclude it via NON_SCOPE_SOURCE_ID_OPS; explicit
--source-id still passes through, explicit --source errors with a hint.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-22 12:14:06 -07:00
Garry TanandClaude Fable 5 ddf0ddc007 test(thin-client): use withEnv() instead of direct process.env mutation (test-isolation R1)
CI verify failed on check:test-isolation — thin-client-source-scope.test.ts
mutated process.env.GBRAIN_SOURCE via beforeEach/afterEach. Wrapped each
test body in withEnv() from test/helpers/with-env.ts instead.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-22 11:04:05 -07:00
SinabinaandClaude Fable 5 f67ff5cd5c fix(thin-client): map --source/GBRAIN_SOURCE/.gbrain-source onto source_id for routed ops (#2098)
The thin-client route short-circuits before makeContext, so the 6-tier
source resolution never ran and `gbrain query --source X` against a
remote brain sent the unknown `source` key verbatim — the server op
ignored it and searched unscoped.

applyThinClientSourceScope now runs the engine-free tiers (flag → env →
dotfile; DB-backed tiers need an engine, and the server's grant scoping
covers the rest) and sets the op's source_id wire param. Ops declaring
their own `source` param are untouched; an explicit --source on an op
with no source_id wire param errors loudly instead of silently dropping;
explicit --source-id/--all-sources on the wire win over ambient tiers.

Fixes #2098

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-21 14:22:59 -07:00
14 changed files with 282 additions and 348 deletions
+65 -12
View File
@@ -24,6 +24,7 @@ import type { GBrainConfig } from './core/config.ts';
import type { AIGatewayConfig } from './core/ai/types.ts';
import type { BrainEngine } from './core/engine.ts';
import { operations, OperationError } from './core/operations.ts';
import { resolveSourceIdEngineFree } from './core/source-resolver.ts';
import { formatVolunteeredPage } from './core/context/volunteer.ts';
import type { Operation, OperationContext } from './core/operations.ts';
import { shouldForceExitAfterMain, finishCliTeardown, flushThenExit, currentExitCode, setCliExitVerdict } from './core/cli-force-exit.ts';
@@ -54,7 +55,7 @@ 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', 'facts', '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', '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.
@@ -382,6 +383,15 @@ async function main() {
if (op.localOnly) {
refuseThinClient(command, cfgPre!.remote_mcp!.mcp_url);
}
// #2098: the local path resolves --source / GBRAIN_SOURCE / .gbrain-source
// inside makeContext (ctx.sourceId), which this route never reaches — so
// scope must be mapped onto the op's source_id wire param before the call.
try {
applyThinClientSourceScope(op, params);
} catch (e: unknown) {
console.error(e instanceof Error ? e.message : String(e));
process.exit(1);
}
await runThinClientRouted(op, params, cfgPre!, cliOpts);
return;
}
@@ -802,6 +812,60 @@ export function parseOpArgs(op: Operation, args: string[]): Record<string, unkno
return params;
}
/**
* #2098: thin-client source scoping. Locally, --source / GBRAIN_SOURCE /
* .gbrain-source resolve to ctx.sourceId in makeContext; the thin-client
* route short-circuits before that, so `gbrain query --source X` against a
* remote brain silently searched unscoped. This runs the engine-free tiers
* (flag → env → dotfile; the DB-backed tiers can't run without an engine —
* the server's grant scoping covers the rest) and maps the result onto the
* op's `source_id` wire param.
*
* Ops that declare their OWN `source` param (facts add, etc.) are left
* untouched — their --source is an op param, not scope. An explicit --source
* on an op with no source_id wire param throws (loud beats silent drop);
* ambient env/dotfile scope with nowhere to send it is ignored, matching the
* pre-fix behavior for non-scopeable ops. Exported for tests.
*/
// Ops whose `source_id` wire param is NOT read-scope semantics: get_skill's
// source_id flips the lookup from host catalog to brain-resident-pack
// (getResidentSkillDetail). Ambient env/dotfile scope must never leak into
// these; an explicit --source-id still passes through untouched above.
const NON_SCOPE_SOURCE_ID_OPS = new Set(['get_skill']);
export function applyThinClientSourceScope(
op: Operation,
params: Record<string, unknown>,
cwd?: string,
): void {
if ('source' in op.params) return; // the op owns --source; not a scope flag
const explicit = typeof params.source === 'string' && params.source.length > 0
? (params.source as string)
: null;
delete params.source; // never a wire param on these ops — don't leak it
// Explicit per-call scope already on the wire wins over ambient tiers.
if (params.source_id !== undefined || params.all_sources === true) {
if (explicit) {
throw new Error('Pass either --source or --source-id/--all-sources, not both.');
}
return;
}
const resolved = resolveSourceIdEngineFree(explicit, cwd);
if (!resolved) return;
if (!('source_id' in op.params) || NON_SCOPE_SOURCE_ID_OPS.has(op.name)) {
if (explicit) {
const hint = NON_SCOPE_SOURCE_ID_OPS.has(op.name)
? `(its source_id parameter is not a scope filter; pass --source-id explicitly if you mean it)`
: `(the remote op has no source_id parameter; the server scopes it to your grant)`;
throw new Error(
`gbrain ${op.cliHints?.name || op.name} does not accept --source on a thin-client install ${hint}.`,
);
}
return; // ambient env/dotfile scope with nowhere to send it
}
params.source_id = resolved;
}
async function makeContext(engine: BrainEngine, params: Record<string, unknown>): Promise<OperationContext> {
// v0.31.8 (D11): resolve sourceId via the canonical 6-tier chain. Honors
// --source / GBRAIN_SOURCE / .gbrain-source / path-match / brain default /
@@ -991,8 +1055,6 @@ 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)
@@ -1028,7 +1090,6 @@ 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.)',
@@ -1858,13 +1919,6 @@ 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
@@ -2345,7 +2399,6 @@ 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)
-48
View File
@@ -1,48 +0,0 @@
/**
* 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 ? `${result.detail}` : ''}\n`,
);
if (result.status === 'failed') setCliExitVerdict(1);
}
+4 -32
View File
@@ -39,7 +39,6 @@ import type { BrainEngine } from '../../core/engine.ts';
import { loadConfig, toEngineConfig } from '../../core/config.ts';
import { createEngine } from '../../core/engine-factory.ts';
import { upsertFactRow, parseFactsFence } from '../../core/facts-fence.ts';
import { resolvePageFilePath } from '../../core/markdown.ts';
let testEngineOverride: BrainEngine | null = null;
export function __setTestEngineOverride(engine: BrainEngine | null): void {
@@ -149,16 +148,9 @@ function isLocalPathDirty(localPath: string): boolean {
}
}
/**
* Exported (not just via `__testing`) because `gbrain facts fence-backfill`
* (#1867) re-runs this phase on demand: remote `extract_facts` deposits that
* predate the fence-write backstop leave row_num-NULL rows the cycle guard
* refuses to reconcile past. The phase is idempotent (only touches
* `row_num IS NULL` rows), so re-running is always safe.
*/
export async function phaseBFenceFacts(
async function phaseBFenceFacts(
engine: BrainEngine | null,
opts: Pick<OrchestratorOpts, 'dryRun'>,
opts: OrchestratorOpts,
): Promise<OrchestratorPhaseResult> {
if (opts.dryRun) {
// Dry-run: report what WOULD happen without touching FS or DB.
@@ -246,11 +238,7 @@ export async function phaseBFenceFacts(
for (const [key, group] of groups) {
const [sourceId, entitySlug] = key.split('\0');
const localPath = localPathById.get(sourceId)!;
// resolvePageFilePath, NOT a bare join — non-default sources fence
// into `<local_path>/.sources/<id>/<slug>.md`, the same path the
// fence-write backstop and put_page write-through compute. A bare
// join here diverges fence and DB for non-default sources (#2044).
const filePath = resolvePageFilePath(localPath, entitySlug, sourceId);
const filePath = join(localPath, `${entitySlug}.md`);
const tmpPath = `${filePath}.tmp`;
try {
@@ -281,21 +269,6 @@ export async function phaseBFenceFacts(
const existingFence = parseFactsFence(body);
const existingKeySet = new Set(existingFence.facts.map(f => `${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${row.source ?? ''}`;
@@ -318,7 +291,6 @@ export async function phaseBFenceFacts(
.toISOString().slice(0, 10)
: undefined;
const { body: updated, rowNum } = upsertFactRow(body, {
rowNum: nextRowNum++,
claim: row.fact,
kind: row.kind,
confidence: row.confidence,
@@ -409,7 +381,7 @@ async function phaseCVerify(
for (const g of groups) {
const localPath = localPathById.get(g.source_id);
if (!localPath) continue;
const filePath = resolvePageFilePath(localPath, g.source_markdown_slug, g.source_id);
const filePath = join(localPath, `${g.source_markdown_slug}.md`);
if (!existsSync(filePath)) {
mismatches.push(`${g.source_markdown_slug} (file missing)`);
continue;
+3 -5
View File
@@ -176,11 +176,9 @@ export async function runExtractFacts(
if (legacyCount > 0) {
result.guardTriggered = true;
result.warnings.push(
`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.`,
`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.`,
);
return result;
}
+6 -7
View File
@@ -1739,14 +1739,13 @@ export interface BrainEngine {
* single-row supersede flow because fence reconciliation is the canonical
* source-of-truth direction, not the consolidator path.
*
* 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.
* 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)`).
*
* Returns the inserted ids in input-order (colliding rows omitted) so
* callers can correlate fence-row → DB-id without a separate lookup.
* Returns the inserted ids in input-order so callers can correlate
* fence-row → DB-id without a separate lookup.
*/
insertFacts(
rows: Array<NewFact & { row_num: number; source_markdown_slug: string }>,
+1 -17
View File
@@ -218,27 +218,11 @@ export async function writeFactsToFence(
}
// 2. Upsert each fact onto the fence in input order. row_num
// 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;
// monotonically increases (max-existing + 1 per call, append-only).
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,
+8 -18
View File
@@ -4102,13 +4102,11 @@ export class PGLiteEngine implements BrainEngine {
): Promise<{ inserted: number; ids: number[] }> {
if (rows.length === 0) return { inserted: 0, ids: [] };
// 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).
// 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.
const ids = await this.db.transaction(async (tx) => {
const out: number[] = [];
for (const input of rows) {
@@ -4151,11 +4149,7 @@ export class PGLiteEngine implements BrainEngine {
$14, $15,
$16, $17, $18, $19,
$20
)
ON CONFLICT (source_id, source_markdown_slug, row_num)
WHERE row_num IS NOT NULL
DO NOTHING
RETURNING id`
) RETURNING id`
: `INSERT INTO facts (
source_id, entity_slug, fact, kind, visibility, notability, context,
valid_from, valid_until, source, source_session, confidence,
@@ -4169,16 +4163,12 @@ export class PGLiteEngine implements BrainEngine {
$15, $16,
$17, $18, $19, $20,
$21
)
ON CONFLICT (source_id, source_markdown_slug, row_num)
WHERE row_num IS NOT NULL
DO NOTHING
RETURNING id`,
) 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],
);
if (ins.rows[0]) out.push(ins.rows[0].id);
out.push(ins.rows[0].id);
}
return out;
});
+6 -12
View File
@@ -4302,12 +4302,10 @@ 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; 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.
// 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).
// 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) => {
@@ -4348,13 +4346,9 @@ export class PostgresEngine implements BrainEngine {
${input.row_num}, ${input.source_markdown_slug},
${claimMetric}, ${claimValue}, ${claimUnit}, ${claimPeriod},
${eventType}
)
ON CONFLICT (source_id, source_markdown_slug, row_num)
WHERE row_num IS NOT NULL
DO NOTHING
RETURNING id
) RETURNING id
`;
if (ins[0]) out.push(Number(ins[0].id));
out.push(Number(ins[0].id));
}
return out;
});
+27
View File
@@ -160,6 +160,33 @@ export async function resolveSourceId(
return 'default';
}
/**
* Engine-free tiers (1-3) of the resolution chain: explicit flag →
* GBRAIN_SOURCE env → .gbrain-source dotfile walk. Used by the thin-client
* CLI path (#2098), which has no local engine to run tiers 4-6 or
* assertSourceExists against — the remote server enforces existence + grant.
* Returns null when no engine-free tier fires.
*/
export function resolveSourceIdEngineFree(
explicit: string | null | undefined,
cwd: string = process.cwd(),
): string | null {
if (explicit) {
if (!SOURCE_ID_RE.test(explicit)) {
throw new Error(`Invalid --source value "${explicit}". Must match [a-z0-9-]{1,32}.`);
}
return explicit;
}
const env = process.env.GBRAIN_SOURCE;
if (env && env.length > 0) {
if (!SOURCE_ID_RE.test(env)) {
throw new Error(`Invalid GBRAIN_SOURCE value "${env}". Must match [a-z0-9-]{1,32}.`);
}
return env;
}
return readDotfileWalk(cwd);
}
/**
* Returns the id of the SINGLE registered non-default source with a
* local_path, when exactly one such row exists. Returns null when:
+1 -3
View File
@@ -304,9 +304,7 @@ describe('runExtractFacts — empty-fence guard (Codex R2-#7)', () => {
expect(r.legacyRowsPending).toBe(1);
expect(r.factsInserted).toBe(0);
expect(r.factsDeleted).toBe(0);
// #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);
expect(r.warnings.some(w => w.includes('apply-migrations'))).toBe(true);
// Legacy row was NOT touched.
// eslint-disable-next-line @typescript-eslint/no-explicit-any
-133
View File
@@ -1,133 +0,0 @@
/**
* #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 |');
});
});
-43
View File
@@ -292,49 +292,6 @@ 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.
+19 -18
View File
@@ -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 collision skips only the colliding row (#2044)
* - v51 partial UNIQUE index rolls back the whole batch on a collision
* - 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)
@@ -135,29 +135,30 @@ describe('engine.insertFacts — batch insert', () => {
});
});
test('v51 partial UNIQUE collision skips ONLY the colliding row (#2044)', async () => {
test('v51 partial UNIQUE index rolls back the whole batch on collision', async () => {
// Seed row #1 first.
await engine.insertFacts([fixtureFact(1, { fact: 'seeded' })], { source_id: 'default' });
// 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);
// 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);
// The seeded row survives untouched; the colliding claim is skipped.
// Verify the transaction rolled back — only the seeded row should remain.
// 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', 'second', 'third']);
expect(rows.rows.map((r: { fact: string }) => r.fact)).toEqual(['seeded']);
});
test('different source_markdown_slug values DO NOT collide on the same row_num', async () => {
+142
View File
@@ -0,0 +1,142 @@
/**
* #2098: thin-client routing dropped --source / GBRAIN_SOURCE / .gbrain-source.
*
* The local CLI path resolves source scope in makeContext (ctx.sourceId); the
* thin-client route short-circuits before that and sent params verbatim, so
* `gbrain query --source X` against a remote brain silently searched unscoped
* (the server op ignores the unknown `source` key).
*
* applyThinClientSourceScope runs the engine-free tiers (flag → env → dotfile)
* and maps the result onto the op's `source_id` wire param. These tests fail
* without the fix (params.source_id stays undefined / params.source leaks).
*/
import { describe, test, expect } from 'bun:test';
import { mkdtempSync, rmSync, writeFileSync } from 'fs';
import { join } from 'path';
import { tmpdir } from 'os';
import { applyThinClientSourceScope, parseOpArgs } from '../src/cli.ts';
import { operationsByName } from '../src/core/operations.ts';
import { withEnv } from './helpers/with-env.ts';
const queryOp = operationsByName.query;
describe('applyThinClientSourceScope (#2098)', () => {
test('--source maps onto the query op wire param source_id', async () => {
await withEnv({ GBRAIN_SOURCE: undefined }, () => {
const params = parseOpArgs(queryOp, ['find things', '--source', 'wiki']);
expect(params.source).toBe('wiki'); // pre-fix state: wrong key
applyThinClientSourceScope(queryOp, params, '/');
expect(params.source_id).toBe('wiki');
expect('source' in params).toBe(false); // never leaks the unknown key
});
});
test('GBRAIN_SOURCE env tier fires when no flag is passed', async () => {
await withEnv({ GBRAIN_SOURCE: 'gstack' }, () => {
const params = parseOpArgs(queryOp, ['find things']);
applyThinClientSourceScope(queryOp, params, '/');
expect(params.source_id).toBe('gstack');
});
});
test('.gbrain-source dotfile tier fires when flag and env are absent', async () => {
await withEnv({ GBRAIN_SOURCE: undefined }, () => {
const tmp = mkdtempSync(join(tmpdir(), 'gbrain-thin-scope-'));
try {
writeFileSync(join(tmp, '.gbrain-source'), 'essays\n');
const params = parseOpArgs(queryOp, ['find things']);
applyThinClientSourceScope(queryOp, params, tmp);
expect(params.source_id).toBe('essays');
} finally {
rmSync(tmp, { recursive: true, force: true });
}
});
});
test('explicit --source-id on the wire wins over ambient env scope', async () => {
await withEnv({ GBRAIN_SOURCE: 'gstack' }, () => {
const params = parseOpArgs(queryOp, ['find things', '--source-id', 'wiki']);
applyThinClientSourceScope(queryOp, params, '/');
expect(params.source_id).toBe('wiki');
});
});
test('--source together with --source-id is rejected loudly', async () => {
await withEnv({ GBRAIN_SOURCE: undefined }, () => {
const params = parseOpArgs(queryOp, ['q', '--source', 'a', '--source-id', 'b']);
expect(() => applyThinClientSourceScope(queryOp, params, '/')).toThrow(/not both/);
});
});
test('invalid --source value is rejected loudly', async () => {
await withEnv({ GBRAIN_SOURCE: undefined }, () => {
const params = parseOpArgs(queryOp, ['q', '--source', 'Bad_Value!']);
expect(() => applyThinClientSourceScope(queryOp, params, '/')).toThrow(/Invalid --source/);
});
});
test('--source on an op with no source_id wire param errors instead of silently dropping', async () => {
await withEnv({ GBRAIN_SOURCE: undefined }, () => {
const op = operationsByName.add_tag;
expect('source_id' in op.params).toBe(false);
const params = { slug: 'x', tag: 'y', source: 'wiki' };
expect(() => applyThinClientSourceScope(op, params, '/')).toThrow(/--source/);
});
});
test('ambient env scope on an op with no source_id wire param is ignored (no throw)', async () => {
await withEnv({ GBRAIN_SOURCE: 'wiki' }, () => {
const op = operationsByName.add_tag;
const params: Record<string, unknown> = { slug: 'x', tag: 'y' };
applyThinClientSourceScope(op, params, '/');
expect(params.source_id).toBeUndefined();
});
});
test('ops that declare their OWN source param are left untouched', async () => {
await withEnv({ GBRAIN_SOURCE: undefined }, () => {
const op = operationsByName.put_raw_data;
expect('source' in op.params).toBe(true);
const params: Record<string, unknown> = { slug: 'x', source: 'crustdata', data: {} };
applyThinClientSourceScope(op, params, '/');
expect(params.source).toBe('crustdata');
expect(params.source_id).toBeUndefined();
});
});
test('get_skill: ambient scope never leaks into its non-scope source_id param', async () => {
await withEnv({ GBRAIN_SOURCE: 'wiki' }, () => {
const op = operationsByName.get_skill;
expect('source_id' in op.params).toBe(true); // has the param, but it is a mode switch
const params: Record<string, unknown> = { name: 'ingest' };
applyThinClientSourceScope(op, params, '/');
expect(params.source_id).toBeUndefined(); // would flip host catalog → brain-pack lookup
});
});
test('get_skill: explicit --source errors instead of masquerading as --source-id', async () => {
await withEnv({ GBRAIN_SOURCE: undefined }, () => {
const op = operationsByName.get_skill;
const params: Record<string, unknown> = { name: 'ingest', source: 'wiki' };
expect(() => applyThinClientSourceScope(op, params, '/')).toThrow(/--source-id/);
});
});
test('get_skill: explicit --source-id passes through untouched', async () => {
await withEnv({ GBRAIN_SOURCE: 'gstack' }, () => {
const op = operationsByName.get_skill;
const params: Record<string, unknown> = { name: 'ingest', source_id: 'wiki' };
applyThinClientSourceScope(op, params, '/');
expect(params.source_id).toBe('wiki');
});
});
test('no scope from any tier leaves params unchanged', async () => {
await withEnv({ GBRAIN_SOURCE: undefined }, () => {
const params = parseOpArgs(queryOp, ['find things']);
applyThinClientSourceScope(queryOp, params, '/');
expect(params.source_id).toBeUndefined();
});
});
});