Compare commits

..
Author SHA1 Message Date
Garry TanandClaude Fable 5 52fffc7ecc fix(facts): seed phase B backfill row_nums past the DB max (#2044 class)
phaseBFenceFacts appended at fence-max+1 with no DB seeding, so on a
diverged page (stamped DB rows + missing fence at the resolved path —
the same divergence class the writeFactsToFence fix handles) the
post-rename UPDATE hit idx_facts_fence_key, the page failed, and the
already-renamed fence disagreed with the DB while the row_num-NULL
backlog persisted. Seed appended row_nums from MAX(fence max, DB max)
per (source_id, slug), mirroring the fence-write fix. Repro test added.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-22 11:46:22 -07:00
Garry TanandClaude Fable 5 039b97df36 fix(facts): route exit codes through setCliExitVerdict
The cli-exit-verdict-pin guard requires every exit-code write in src/
to go through setCliExitVerdict (raw process.exitCode assignments get
zeroed by the owned-verdict read on PGLite). Replace the two raw
assignments in the new facts command.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-22 10:50:45 -07:00
Garry TanandClaude Fable 5 2bb3424863 fix(facts): idempotent fence deposits + re-runnable fence-backfill command
Two fixes for the remote extract_facts deposit path:

#2044 — a second deposit to an already-fenced page could throw
idx_facts_fence_key and roll back the whole batch when fence and DB
row_nums diverged (e.g. legacy wrong-path fence writes). writeFactsToFence
now seeds the next row_num from MAX(fence max, DB max(row_num)) for the
(source_id, slug) pair, and insertFacts in BOTH engines adds
ON CONFLICT (source_id, source_markdown_slug, row_num) WHERE row_num IS
NOT NULL DO NOTHING so a residual collision skips one row instead of
failing the batch.

#1867 — row_num-NULL backlogs (remote deposits that predate the fence
backstop) had no remedy: the fence backfill lived only inside the one-shot
v0_32_2 migration, and the cycle guard pointed at `gbrain apply-migrations
--yes`, which never re-runs a completed migration. phaseBFenceFacts (already
idempotent on row_num IS NULL) is now exported and exposed as
`gbrain facts fence-backfill [--dry-run]`; the guard message points at it.
The backfill also routes page paths through resolvePageFilePath so
non-default sources fence into the same path the fence-write backstop uses.

Fixes #2044
Fixes #1867

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-21 14:45:53 -07:00
25 changed files with 385 additions and 261 deletions
+12 -1
View File
@@ -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.
@@ -991,6 +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)
@@ -1026,6 +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.)',
@@ -1855,6 +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
@@ -2335,6 +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)
+48
View File
@@ -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 ? `${result.detail}` : ''}\n`,
);
if (result.status === 'failed') setCliExitVerdict(1);
}
+32 -4
View File
@@ -39,6 +39,7 @@ import type { BrainEngine } from '../../core/engine.ts';
import { loadConfig, toEngineConfig } from '../../core/config.ts';
import { createEngine } from '../../core/engine-factory.ts';
import { upsertFactRow, parseFactsFence } from '../../core/facts-fence.ts';
import { resolvePageFilePath } from '../../core/markdown.ts';
let testEngineOverride: BrainEngine | null = null;
export function __setTestEngineOverride(engine: BrainEngine | null): void {
@@ -148,9 +149,16 @@ function isLocalPathDirty(localPath: string): boolean {
}
}
async function phaseBFenceFacts(
/**
* Exported (not just via `__testing`) because `gbrain facts fence-backfill`
* (#1867) re-runs this phase on demand: remote `extract_facts` deposits that
* predate the fence-write backstop leave row_num-NULL rows the cycle guard
* refuses to reconcile past. The phase is idempotent (only touches
* `row_num IS NULL` rows), so re-running is always safe.
*/
export async function phaseBFenceFacts(
engine: BrainEngine | null,
opts: OrchestratorOpts,
opts: Pick<OrchestratorOpts, 'dryRun'>,
): Promise<OrchestratorPhaseResult> {
if (opts.dryRun) {
// Dry-run: report what WOULD happen without touching FS or DB.
@@ -238,7 +246,11 @@ async function phaseBFenceFacts(
for (const [key, group] of groups) {
const [sourceId, entitySlug] = key.split('\0');
const localPath = localPathById.get(sourceId)!;
const filePath = join(localPath, `${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;
+3 -13
View File
@@ -18,22 +18,12 @@
import { loadConfig } from '../config.ts';
export function hasAnthropicKey(): boolean {
return resolveAnthropicKey() !== undefined;
}
/**
* Resolve the actual key value: env first, then the gbrain config file.
* Callers constructing an Anthropic client directly (e.g. the legacy
* subagent path) must pass this as `apiKey` — a bare `new Anthropic()`
* only sees env, so launchd/MCP workers with config-stored keys fail.
*/
export function resolveAnthropicKey(): string | undefined {
if (process.env.ANTHROPIC_API_KEY) return process.env.ANTHROPIC_API_KEY;
if (process.env.ANTHROPIC_API_KEY) return true;
try {
const cfg = loadConfig();
if (cfg?.anthropic_api_key) return cfg.anthropic_api_key;
if (cfg?.anthropic_api_key) return true;
} catch {
// loadConfig may throw on first-run installs; treat as no key available.
}
return undefined;
return false;
}
+5 -3
View File
@@ -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
View File
@@ -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 }>,
+17 -1
View File
@@ -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,
+1 -5
View File
@@ -48,7 +48,6 @@ import {
logSubagentHeartbeat,
} from './subagent-audit.ts';
import { resolveModel, isAnthropicProvider, TIER_DEFAULTS } from '../../model-config.ts';
import { resolveAnthropicKey } from '../../ai/anthropic-key.ts';
import { buildSystemPrompt, DEFAULT_SUBAGENT_SYSTEM } from '../system-prompt.ts';
import { toolLoop as gatewayToolLoop } from '../../ai/gateway.ts';
import type { ChatToolDef, ChatMessage, ChatBlock, ChatResult, ToolHandler } from '../../ai/gateway.ts';
@@ -187,10 +186,7 @@ export function makeSubagentHandler(deps: SubagentDeps) {
// lives at sdk.messages.create. Assigning sdk.messages directly gets the
// right object; JS method-call semantics preserve `this` at the call
// site (subagent.ts invokes client.create(...) with client === sdk.messages).
// Resolve the key env-first, then config (anthropic_api_key) — a bare
// new Anthropic() only reads env, so launchd/MCP workers whose key lives
// in the gbrain config file would fail auth (#2048).
const makeAnthropic = deps.makeAnthropic ?? (() => new Anthropic({ apiKey: resolveAnthropicKey() }));
const makeAnthropic = deps.makeAnthropic ?? (() => new Anthropic());
const client: MessagesClient = deps.client ?? makeAnthropic().messages;
const config = deps.config ?? loadConfig() ?? ({ engine: 'postgres' } as GBrainConfig);
const rateLeaseKey = deps.rateLeaseKey ?? DEFAULT_RATE_KEY;
+1 -2
View File
@@ -4562,8 +4562,7 @@ const list_schema_packs: Operation = {
const { existsSync, readdirSync } = await import('node:fs');
const { join } = await import('node:path');
const { gbrainPath } = await import('./config.ts');
const { BUNDLED_PACK_NAMES } = await import('./schema-pack/bundled.ts');
const bundled = [...BUNDLED_PACK_NAMES];
const bundled = ['gbrain-base', 'gbrain-recommended'];
const installedDir = gbrainPath('schema-packs');
const installed: string[] = [];
if (existsSync(installedDir)) {
+18 -8
View File
@@ -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;
});
+12 -6
View File
@@ -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;
});
-24
View File
@@ -1,24 +0,0 @@
// Bundled schema-pack registry — single source of truth for the packs that
// ship in src/core/schema-pack/base/. Keep every bundled-pack consumer
// (CLI/MCP inspection, active-pack loading, mutation guards, upgrade
// discovery) on this one list so they cannot drift.
//
// v0.39 T8 — gbrain-base + gbrain-recommended.
// v0.41 T4 — lens packs: creator, investor, engineer, everything (meta-pack).
// v0.42 type-unification — gbrain-base-v2, the 15-type canonical successor.
export const BUNDLED_PACK_NAMES = [
'gbrain-base',
'gbrain-recommended',
'gbrain-creator',
'gbrain-investor',
'gbrain-engineer',
'gbrain-everything',
'gbrain-base-v2',
] as const;
export type BundledPackName = typeof BUNDLED_PACK_NAMES[number];
export function isBundledPackName(name: string): name is BundledPackName {
return (BUNDLED_PACK_NAMES as readonly string[]).includes(name);
}
+22 -2
View File
@@ -37,7 +37,6 @@ import {
type ResolutionInput,
type ResolutionResult,
} from './registry.ts';
import { isBundledPackName } from './bundled.ts';
/**
* Inputs the caller (operations.ts handler / engine query path) provides.
@@ -93,7 +92,28 @@ export function _resetPackLocatorForTests(): void {
* throwing UnknownPackError with a paste-ready install hint.
*/
function defaultPackLocator(name: string): string | null {
if (isBundledPackName(name)) {
// v0.39 T8 — bundled packs registry. gbrain-base + gbrain-recommended
// ship in src/core/schema-pack/base/. Add a new entry here to bundle
// additional canonical packs.
//
// v0.41 T4 — lens packs join the bundle: creator (atoms + concepts +
// extract_atoms/synthesize_concepts phases), investor (theses + bet
// resolution + 3 calibration domains), engineer (gstack-learnings bridge
// + 3 calibration domains), everything (meta-pack stacking all three
// via extends + borrow_from). Each ships as a real YAML at base/<name>.yaml.
const BUNDLED: ReadonlyArray<string> = [
'gbrain-base',
'gbrain-recommended',
'gbrain-creator',
'gbrain-investor',
'gbrain-engineer',
'gbrain-everything',
// v0.42 type-unification: 15-type canonical successor to gbrain-base.
// Ships as install default (Lane E T17) + via gbrain onboard pack
// upgrade flow (the unify-types Minion handler).
'gbrain-base-v2',
];
if (BUNDLED.includes(name)) {
// Resolve bundled YAML relative to this source file. Works in both
// direct-bun execution and bun --compile binaries.
const here = dirname(fileURLToPath(import.meta.url));
-31
View File
@@ -159,29 +159,6 @@ export function parseYamlMini(content: string): unknown {
return parseMapping(baseIndent);
}
function parseBlockScalar(parentIndent: number, folded: boolean): string {
const contentIndent = parentIndent + 2;
const out: string[] = [];
while (i < lines.length) {
const raw = lines[i];
// Inside a block scalar everything is literal content — '#' is NOT a
// comment here, so use the raw line (no stripComment / isBlank).
if (raw.trim() === '') {
out.push('');
i++;
continue;
}
const indent = indentOf(raw);
if (indent <= parentIndent) break;
out.push(raw.slice(Math.min(contentIndent, indent)));
i++;
}
if (folded) {
return out.join(' ').replace(/\s+$/u, '');
}
return out.join('\n').replace(/\n+$/u, '');
}
function parseSequence(baseIndent: number): unknown[] {
const result: unknown[] = [];
while (i < lines.length) {
@@ -250,10 +227,6 @@ export function parseYamlMini(content: string): unknown {
i++;
if (rest2 === '') {
map[key2] = parseBlock(nextIndent + 2);
} else if (rest2 === '|' || rest2 === '|-' || rest2 === '|+') {
map[key2] = parseBlockScalar(nextIndent, false);
} else if (rest2 === '>' || rest2 === '>-' || rest2 === '>+') {
map[key2] = parseBlockScalar(nextIndent, true);
} else {
map[key2] = parseScalar(rest2);
}
@@ -284,10 +257,6 @@ export function parseYamlMini(content: string): unknown {
i++;
if (rest === '') {
result[key] = parseBlock(indent + 2);
} else if (rest === '|' || rest === '|-' || rest === '|+') {
result[key] = parseBlockScalar(indent, false);
} else if (rest === '>' || rest === '>-' || rest === '>+') {
result[key] = parseBlockScalar(indent, true);
} else {
result[key] = parseScalar(rest);
}
+1 -2
View File
@@ -65,7 +65,6 @@ import { invalidateQueryCache } from './query-cache-invalidator.ts';
import { logMutationFailure, logMutationSuccess, type MutationActor, type MutationOp } from './mutate-audit.ts';
import { runFilePlaneLintRules } from './lint-rules.ts';
import { withPackLock, type PackLockOpts } from './pack-lock.ts';
import { BUNDLED_PACK_NAMES as BUNDLED_PACK_NAME_LIST } from './bundled.ts';
import type { BrainEngine } from '../engine.ts';
export type PackFileFormat = 'json' | 'yaml';
@@ -94,7 +93,7 @@ export class SchemaPackMutationError extends Error {
}
}
export const BUNDLED_PACK_NAMES = new Set<string>(BUNDLED_PACK_NAME_LIST);
export const BUNDLED_PACK_NAMES = new Set(['gbrain-base', 'gbrain-recommended', 'gbrain-base-v2']);
export interface MutateResult {
/** Pack name that was mutated. */
+1 -33
View File
@@ -10,7 +10,7 @@ import { mkdtempSync, mkdirSync, writeFileSync, rmSync } from 'node:fs';
import { tmpdir } from 'node:os';
import { join } from 'node:path';
import { withEnv } from '../helpers/with-env.ts';
import { hasAnthropicKey, resolveAnthropicKey } from '../../src/core/ai/anthropic-key.ts';
import { hasAnthropicKey } from '../../src/core/ai/anthropic-key.ts';
const tmpDirs: string[] = [];
function freshHome(withConfig?: Record<string, unknown>): string {
@@ -62,35 +62,3 @@ describe('hasAnthropicKey', () => {
);
});
});
describe('resolveAnthropicKey (#2048 — subagent config-key auth)', () => {
test('env wins over config', async () => {
const home = freshHome({ anthropic_api_key: 'sk-from-config' });
await withEnv(
{ ANTHROPIC_API_KEY: 'sk-from-env', GBRAIN_HOME: home, DATABASE_URL: undefined, GBRAIN_DATABASE_URL: undefined },
async () => {
expect(resolveAnthropicKey()).toBe('sk-from-env');
},
);
});
test('config key returned when env unset', async () => {
const home = freshHome({ anthropic_api_key: 'sk-from-config' });
await withEnv(
{ ANTHROPIC_API_KEY: undefined, GBRAIN_HOME: home, DATABASE_URL: undefined, GBRAIN_DATABASE_URL: undefined },
async () => {
expect(resolveAnthropicKey()).toBe('sk-from-config');
},
);
});
test('neither → undefined', async () => {
const home = freshHome();
await withEnv(
{ ANTHROPIC_API_KEY: undefined, GBRAIN_HOME: home, DATABASE_URL: undefined, GBRAIN_DATABASE_URL: undefined },
async () => {
expect(resolveAnthropicKey()).toBeUndefined();
},
);
});
});
+3 -1
View File
@@ -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
+133
View File
@@ -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 |');
});
});
+43
View File
@@ -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.
+18 -19
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 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 () => {
+6 -6
View File
@@ -55,13 +55,13 @@ describe('v0.41 T4: all 4 bundled lens packs parse cleanly', () => {
});
describe('v0.41 T4: bundled registry includes lens packs', () => {
test('BUNDLED_PACK_NAMES includes the 4 lens pack names', async () => {
// The bundled list moved from load-active.ts to bundled.ts (the
// single source of truth); assert the array directly instead of
// grepping source text.
const { BUNDLED_PACK_NAMES } = await import('../src/core/schema-pack/bundled.ts');
test('load-active.ts BUNDLED array source includes the 4 lens pack names', () => {
const loadActiveSrc = readFileSync(
join(here, '..', 'src', 'core', 'schema-pack', 'load-active.ts'),
'utf-8',
);
for (const name of PACK_NAMES) {
expect(BUNDLED_PACK_NAMES).toContain(name);
expect(loadActiveSrc).toContain(`'${name}'`);
}
});
});
-3
View File
@@ -149,9 +149,6 @@ describe('list_schema_packs', () => {
seedPack('mine');
const result = await operationsByName.list_schema_packs!.handler(ctxOf(), {}) as { bundled: string[]; installed: string[] };
expect(result.bundled).toContain('gbrain-base');
expect(result.bundled).toContain('gbrain-recommended');
expect(result.bundled).toContain('gbrain-base-v2');
expect(result.bundled).toContain('gbrain-investor');
expect(result.installed).toContain('mine');
});
});
+1 -38
View File
@@ -64,14 +64,11 @@ describe('gbrain schema CLI (Phase C)', () => {
expect(r.stdout + r.stderr).toMatch(/schema|active|list|show|validate|use/i);
});
test('schema list shows all bundled packs', () => {
test('schema list shows gbrain-base bundled', () => {
const r = gbrain(['schema', 'list']);
expect(r.code).toBe(0);
expect(r.stdout).toContain('Bundled packs:');
expect(r.stdout).toContain('gbrain-base');
expect(r.stdout).toContain('gbrain-recommended');
expect(r.stdout).toContain('gbrain-base-v2');
expect(r.stdout).toContain('gbrain-investor');
});
test('schema show gbrain-base prints manifest details', () => {
@@ -100,40 +97,6 @@ describe('gbrain schema CLI (Phase C)', () => {
expect(r.stdout).toContain('valid manifest');
});
test('schema show/validate exposes bundled gbrain-recommended', () => {
const show = gbrain(['schema', 'show', 'gbrain-recommended']);
expect(show.code).toBe(0);
expect(show.stdout).toContain('gbrain-recommended v1.0.0');
expect(show.stdout).toContain('Page types (');
expect(show.stdout).toContain('meeting :: temporal');
const validate = gbrain(['schema', 'validate', 'gbrain-recommended']);
expect(validate.code).toBe(0);
expect(validate.stdout).toContain('valid manifest');
});
test('schema show exposes bundled gbrain-base-v2 successor pack', () => {
const r = gbrain(['schema', 'show', 'gbrain-base-v2']);
expect(r.code).toBe(0);
expect(r.stdout).toContain('gbrain-base-v2 v1.0.0');
expect(r.stdout).toContain('Page types (');
expect(r.stdout).toContain('Link verbs (14)');
});
test('schema active loads configured gbrain-recommended with real types', () => {
const home = mkdtempSync(join(tmpdir(), 'gbrain-schema-active-recommended-'));
try {
mkdirSync(join(home, '.gbrain'), { recursive: true });
writeFileSync(join(home, '.gbrain', 'config.json'), JSON.stringify({ schema_pack: 'gbrain-recommended' }), 'utf-8');
const r = gbrain(['schema', 'active'], { GBRAIN_HOME: home });
expect(r.code).toBe(0);
expect(r.stdout).toContain('Active pack: gbrain-recommended');
expect(r.stdout).not.toContain('Page types: 0');
} finally {
rmSync(home, { recursive: true, force: true });
}
});
test('schema active reports default resolution', () => {
const r = gbrain(['schema', 'active']);
expect(r.code).toBe(0);
-49
View File
@@ -345,34 +345,6 @@ describe('YAML mini-parser', () => {
expect(result.types[1].weight).toBe(2);
});
test('parses block scalar without swallowing following keys', () => {
const yaml = `name: blocky
description: |
First line.
Second line.
page_types:
- name: meeting
primitive: temporal
path_prefixes:
- meetings/
aliases: []
extractable: true
expert_routing: false`;
const result = parseYamlMini(yaml) as { description: string; page_types: Array<Record<string, unknown>> };
expect(result.description).toBe('First line.\nSecond line.');
expect(result.page_types).toHaveLength(1);
expect(result.page_types[0].name).toBe('meeting');
});
test('block scalar keeps # as literal content, not a comment', () => {
const yaml = `description: |
See issue #2029 for context.
name: hashy`;
const result = parseYamlMini(yaml) as Record<string, unknown>;
expect(result.description).toBe('See issue #2029 for context.');
expect(result.name).toBe('hashy');
});
test('strips comments', () => {
const result = parseYamlMini('# top comment\nname: value # inline comment') as Record<string, unknown>;
expect(result.name).toBe('value');
@@ -402,27 +374,6 @@ extends: null`;
const pack = loadPackFromString(json, 'fixture.json');
expect(pack.name).toBe('json-pack');
});
test('loads block-scalar pack descriptions without losing page types', () => {
const pack = loadPackFromString(`api_version: gbrain-schema-pack-v1
name: recommended-fixture
version: 1.0.0
extends: gbrain-base
description: |
Operational starter pack.
page_types:
- name: meeting
primitive: temporal
path_prefixes:
- meetings/
aliases: []
extractable: true
expert_routing: false
link_types: []`, 'fixture.yaml');
expect(pack.name).toBe('recommended-fixture');
expect(pack.extends).toBe('gbrain-base');
expect(pack.page_types.map((t) => t.name)).toContain('meeting');
});
});
describe('ReDoS guard', () => {
+1 -4
View File
@@ -103,10 +103,7 @@ describe('locateMutablePackFile — bundled guard', () => {
expect(BUNDLED_PACK_NAMES.has('gbrain-recommended')).toBe(true);
// v0.42 (T22): gbrain-base-v2 joins the bundled set.
expect(BUNDLED_PACK_NAMES.has('gbrain-base-v2')).toBe(true);
// Derived from the single bundled registry — the lens packs (creator,
// investor, engineer, everything) are read-only too.
expect(BUNDLED_PACK_NAMES.has('gbrain-investor')).toBe(true);
expect(BUNDLED_PACK_NAMES.size).toBe(7);
expect(BUNDLED_PACK_NAMES.size).toBe(3);
});
it('rejects gbrain-base-v2 with PACK_READONLY (bundled guard)', () => {