mirror of
https://github.com/garrytan/gbrain.git
synced 2026-08-16 18:02:30 +00:00
Compare commits
1
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
58683eb9ac |
+1
-12
@@ -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', '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.
|
||||
@@ -991,8 +991,6 @@ 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 +1026,6 @@ 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 +1855,6 @@ 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 +2335,6 @@ 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)
|
||||
|
||||
@@ -19,7 +19,7 @@
|
||||
*/
|
||||
|
||||
import type { BrainEngine } from '../core/engine.ts';
|
||||
import { runPhaseCalibrationProfile } from '../core/cycle/calibration-profile.ts';
|
||||
import { resolveCalibrationHolder, runPhaseCalibrationProfile } from '../core/cycle/calibration-profile.ts';
|
||||
import { sourceScopeOpts, type OperationContext } from '../core/operations.ts';
|
||||
import type { GBrainConfig } from '../core/config.ts';
|
||||
import { GBrainError } from '../core/types.ts';
|
||||
@@ -167,7 +167,7 @@ export async function runCalibration(
|
||||
config: GBrainConfig,
|
||||
): Promise<void> {
|
||||
const { opts } = parseArgs(args);
|
||||
const holder = opts.holder ?? 'garry';
|
||||
const holder = await resolveCalibrationHolder(engine, opts.holder);
|
||||
// Resolve --source / GBRAIN_SOURCE / .gbrain-source so the (now reachable, #2035)
|
||||
// calibration command targets the right source in a multi-source brain instead
|
||||
// of always reading `default`. No signal → 'default' (prior behavior).
|
||||
@@ -253,14 +253,14 @@ export async function getCalibrationProfileOp(
|
||||
ctx: OperationContext,
|
||||
params: { holder?: string },
|
||||
): Promise<CalibrationProfileRow | null> {
|
||||
const holder = params.holder ?? 'garry';
|
||||
if (typeof holder !== 'string' || holder.length === 0) {
|
||||
if (params.holder !== undefined && (typeof params.holder !== 'string' || params.holder.length === 0)) {
|
||||
throw new GBrainError(
|
||||
'INVALID_HOLDER',
|
||||
'get_calibration_profile.holder must be a non-empty string',
|
||||
'pass holder="<slug>" or omit to default to "garry"',
|
||||
'pass holder="<slug>" or omit to default to the calibration.user_holder config (then "garry")',
|
||||
);
|
||||
}
|
||||
const holder = await resolveCalibrationHolder(ctx.engine, params.holder);
|
||||
const scope = sourceScopeOpts(ctx);
|
||||
return getLatestProfile(ctx.engine, { holder, ...scope });
|
||||
}
|
||||
|
||||
@@ -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);
|
||||
}
|
||||
@@ -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;
|
||||
|
||||
@@ -928,6 +928,10 @@ export const KNOWN_CONFIG_KEYS: readonly string[] = [
|
||||
// Emotional weight (v0.29)
|
||||
'emotional_weight.high_tags',
|
||||
'emotional_weight.user_holder',
|
||||
// Calibration holder (#1726): persistent default for the nightly
|
||||
// calibration_profile phase + `gbrain calibration`, symmetric with
|
||||
// emotional_weight.user_holder. Falls back to 'garry' when unset.
|
||||
'calibration.user_holder',
|
||||
// Cycle phase config
|
||||
'cycle.grade_takes.write_gstack_learnings',
|
||||
// Content sanity (v0.41)
|
||||
|
||||
@@ -96,7 +96,7 @@ export type PatternStatementsGenerator = (input: {
|
||||
export type BiasTagsGenerator = (patterns: string[]) => Promise<string[]>;
|
||||
|
||||
export interface CalibrationProfileOpts extends BasePhaseOpts {
|
||||
/** Holder to generate the profile for. Default 'garry'. */
|
||||
/** Holder to generate the profile for. Default: `calibration.user_holder` config, then 'garry'. */
|
||||
holder?: string;
|
||||
/** Inject the patterns generator (tests). */
|
||||
patternsGenerator?: PatternStatementsGenerator;
|
||||
@@ -194,6 +194,26 @@ export function parseBiasTagsOutput(raw: string): string[] {
|
||||
.slice(0, 4);
|
||||
}
|
||||
|
||||
/**
|
||||
* #1726: resolve the calibration holder. Explicit param wins, then the
|
||||
* persistent `calibration.user_holder` config key (symmetric with
|
||||
* emotional_weight.user_holder), then the legacy 'garry' default. Fail-open:
|
||||
* a missing config table / mock engine without getConfig falls through.
|
||||
*/
|
||||
export async function resolveCalibrationHolder(
|
||||
engine: BrainEngine,
|
||||
explicit?: string,
|
||||
): Promise<string> {
|
||||
if (explicit) return explicit;
|
||||
try {
|
||||
const configured = await engine.getConfig('calibration.user_holder');
|
||||
if (configured && configured.trim().length > 0) return configured.trim();
|
||||
} catch {
|
||||
// Config unavailable — use the legacy default.
|
||||
}
|
||||
return 'garry';
|
||||
}
|
||||
|
||||
/** Pick the "loudest" pattern slot for the template fallback. */
|
||||
function pickFallbackSlots(scorecard: TakesScorecard): PatternStatementSlots {
|
||||
if (!scorecard || scorecard.resolved === 0) {
|
||||
@@ -227,7 +247,7 @@ class CalibrationProfilePhase extends BaseCyclePhase {
|
||||
_ctx: OperationContext,
|
||||
opts: CalibrationProfileOpts,
|
||||
): Promise<{ summary: string; details: Record<string, unknown>; status?: PhaseStatus }> {
|
||||
const holder = opts.holder ?? 'garry';
|
||||
const holder = await resolveCalibrationHolder(engine, opts.holder);
|
||||
const promptVersion = opts.promptVersion ?? CALIBRATION_PROFILE_PROMPT_VERSION;
|
||||
const modelId = opts.model ?? TIER_DEFAULTS.reasoning;
|
||||
const gradeCompletion = opts.gradeCompletion ?? 1.0;
|
||||
|
||||
@@ -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
@@ -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 }>,
|
||||
|
||||
@@ -68,11 +68,14 @@ export async function extractTimelineFromMeetings(
|
||||
// 1. Fetch all meeting pages (one round-trip).
|
||||
const sourceFilter = opts.sourceIdFilter ? `AND source_id = $1` : '';
|
||||
const meetingParams = opts.sourceIdFilter ? [opts.sourceIdFilter] : [];
|
||||
// #2109: gbrain-base-v2's unify-types catch-all retypes meeting pages to
|
||||
// `note` with frontmatter.legacy_type = 'meeting'. Match both spellings so
|
||||
// the extractor keeps working on migrated (v2) brains, not just v1 ones.
|
||||
const meetings = await engine.executeRaw<MeetingRow>(
|
||||
`SELECT slug, source_id, title, effective_date, updated_at,
|
||||
compiled_truth, COALESCE(timeline, '') AS timeline
|
||||
FROM pages
|
||||
WHERE type = 'meeting'
|
||||
WHERE (type = 'meeting' OR frontmatter ->> 'legacy_type' = 'meeting')
|
||||
AND deleted_at IS NULL
|
||||
${sourceFilter}
|
||||
ORDER BY effective_date DESC NULLS LAST, slug`,
|
||||
@@ -94,7 +97,7 @@ export async function extractTimelineFromMeetings(
|
||||
JOIN pages pf ON pf.id = l.from_page_id
|
||||
JOIN pages pt ON pt.id = l.to_page_id
|
||||
WHERE l.link_type = 'attended'
|
||||
AND pf.type = 'meeting'
|
||||
AND (pf.type = 'meeting' OR pf.frontmatter ->> 'legacy_type' = 'meeting')
|
||||
AND pf.deleted_at IS NULL
|
||||
AND pt.deleted_at IS NULL`,
|
||||
);
|
||||
|
||||
@@ -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,
|
||||
|
||||
@@ -4562,7 +4562,10 @@ 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 = ['gbrain-base', 'gbrain-recommended'];
|
||||
// #1726: derive from the locator's registry instead of a hand-copied
|
||||
// subset (which had frozen at 2 of 7 bundled packs).
|
||||
const { BUNDLED_PACKS } = await import('./schema-pack/load-active.ts');
|
||||
const bundled = [...BUNDLED_PACKS];
|
||||
const installedDir = gbrainPath('schema-packs');
|
||||
const installed: string[] = [];
|
||||
if (existsSync(installedDir)) {
|
||||
|
||||
@@ -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;
|
||||
});
|
||||
|
||||
@@ -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;
|
||||
});
|
||||
|
||||
@@ -41,6 +41,12 @@ migration_from:
|
||||
pack: gbrain-base
|
||||
version: "1.x"
|
||||
|
||||
# #2117 — cycle-phase participation. `phases:` is additive and pack-gated;
|
||||
# without this key extract_atoms is silently off on v2 brains even though
|
||||
# onboard + doctor recommend it (v2 declares the `atom` type it writes).
|
||||
phases:
|
||||
- extract_atoms
|
||||
|
||||
page_types:
|
||||
- name: person
|
||||
primitive: entity
|
||||
@@ -319,6 +325,10 @@ page_types:
|
||||
extractable: false
|
||||
expert_routing: false
|
||||
|
||||
# #2117 — inference rules ported from gbrain-base v1 so extract-ner keeps
|
||||
# working on v2 brains (it hard-skips with pack_unavailable when no
|
||||
# link_type declares an inference.regex). Same ReDoS-guarded sketch
|
||||
# regexes v1 ships; production matchers in link-extraction.ts still apply.
|
||||
link_types:
|
||||
- name: partner_of
|
||||
inverse: partner_of
|
||||
@@ -328,14 +338,24 @@ link_types:
|
||||
- name: discusses
|
||||
- name: founded
|
||||
inverse: founded_by
|
||||
inference:
|
||||
regex: \b(founded|founder of|co-?founded|started)\b
|
||||
- name: works_at
|
||||
inverse: employs
|
||||
inference:
|
||||
regex: \b(works? at|employed by|works? for|joined|hired by|ceo of|cto of|cmo of)\b
|
||||
- name: invested_in
|
||||
inverse: investor_of
|
||||
inference:
|
||||
regex: \b(invested in|backed|seeded|funded|wrote a check)\b
|
||||
- name: sourced_from
|
||||
- name: derived_from
|
||||
- name: supersedes
|
||||
- name: redirects_to
|
||||
# NOTE: v1's `attended` inference is page_type-bound to `meeting`, which
|
||||
# v2 does not declare (lint: link_types_undeclared_page_type). Meeting
|
||||
# pages retyped by unify-types are matched via frontmatter.legacy_type
|
||||
# in extract-timeline-from-meetings (#2109) instead.
|
||||
- name: attended
|
||||
inverse: attended_by
|
||||
- name: authored
|
||||
|
||||
@@ -91,29 +91,33 @@ export function _resetPackLocatorForTests(): void {
|
||||
* Returns null when the pack is not found. Callers handle null by
|
||||
* throwing UnknownPackError with a paste-ready install hint.
|
||||
*/
|
||||
// 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.
|
||||
//
|
||||
// #1726: exported so reporting surfaces (list_schema_packs) derive from the
|
||||
// same list the locator resolves — no more hand-copied 2-of-7 subsets.
|
||||
export const BUNDLED_PACKS: 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',
|
||||
];
|
||||
|
||||
function defaultPackLocator(name: string): string | null {
|
||||
// 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)) {
|
||||
if (BUNDLED_PACKS.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));
|
||||
|
||||
@@ -32,7 +32,7 @@ interface CapturedSql {
|
||||
params: unknown[];
|
||||
}
|
||||
|
||||
function buildMockEngine(opts: { scorecard: TakesScorecard }): {
|
||||
function buildMockEngine(opts: { scorecard: TakesScorecard; config?: Record<string, string> }): {
|
||||
engine: BrainEngine;
|
||||
captured: CapturedSql[];
|
||||
} {
|
||||
@@ -42,6 +42,9 @@ function buildMockEngine(opts: { scorecard: TakesScorecard }): {
|
||||
async getScorecard() {
|
||||
return opts.scorecard;
|
||||
},
|
||||
async getConfig(key: string) {
|
||||
return opts.config?.[key] ?? null;
|
||||
},
|
||||
async executeRaw<T>(sql: string, params?: unknown[]): Promise<T[]> {
|
||||
captured.push({ sql, params: params ?? [] });
|
||||
return [];
|
||||
@@ -241,6 +244,36 @@ describe('runPhaseCalibrationProfile — phase integration', () => {
|
||||
expect(insert!.params[11]).toEqual(['over-confident-geography']); // active_bias_tags
|
||||
});
|
||||
|
||||
test('#1726: calibration.user_holder config drives the holder when no explicit opt', async () => {
|
||||
const { engine, captured } = buildMockEngine({
|
||||
scorecard: ENOUGH_RESOLVED_SCORECARD,
|
||||
config: { 'calibration.user_holder': 'alice-example' },
|
||||
});
|
||||
await runPhaseCalibrationProfile(buildCtx(engine), {
|
||||
patternsGenerator: async () => ['You call early-stage tactics well — 8 of 10 held up.'],
|
||||
biasTagsGenerator: async () => [],
|
||||
voiceGateJudge: passJudge,
|
||||
});
|
||||
const insert = captured.find(c => c.sql.includes('INSERT INTO calibration_profiles'));
|
||||
expect(insert).toBeDefined();
|
||||
expect(insert!.params[1]).toBe('alice-example'); // holder from config
|
||||
});
|
||||
|
||||
test('#1726: explicit holder opt wins over calibration.user_holder config', async () => {
|
||||
const { engine, captured } = buildMockEngine({
|
||||
scorecard: ENOUGH_RESOLVED_SCORECARD,
|
||||
config: { 'calibration.user_holder': 'alice-example' },
|
||||
});
|
||||
await runPhaseCalibrationProfile(buildCtx(engine), {
|
||||
holder: 'charlie-example',
|
||||
patternsGenerator: async () => ['You call early-stage tactics well — 8 of 10 held up.'],
|
||||
biasTagsGenerator: async () => [],
|
||||
voiceGateJudge: passJudge,
|
||||
});
|
||||
const insert = captured.find(c => c.sql.includes('INSERT INTO calibration_profiles'));
|
||||
expect(insert!.params[1]).toBe('charlie-example');
|
||||
});
|
||||
|
||||
test('default model is a provider-prefixed id, persisted to model_id (#2451)', async () => {
|
||||
const { engine, captured } = buildMockEngine({ scorecard: ENOUGH_RESOLVED_SCORECARD });
|
||||
const patternsGenerator: PatternStatementsGenerator = async () => [
|
||||
|
||||
@@ -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
|
||||
|
||||
@@ -0,0 +1,106 @@
|
||||
// #2109 — gbrain-base-v2's unify-types retypes meeting pages to `note`
|
||||
// with frontmatter.legacy_type='meeting'. extract-timeline-from-meetings
|
||||
// used to hardcode type='meeting' and silently scan 0 meetings on migrated
|
||||
// brains. These tests fail without the legacy_type fallback in both SQL
|
||||
// sites (meeting walk + attended-edge join).
|
||||
|
||||
import { afterAll, beforeAll, beforeEach, describe, expect, it } from 'bun:test';
|
||||
import { PGLiteEngine } from '../src/core/pglite-engine.ts';
|
||||
import { resetPgliteState } from './helpers/reset-pglite.ts';
|
||||
import { extractTimelineFromMeetings } from '../src/core/extract-timeline-from-meetings.ts';
|
||||
|
||||
let engine: PGLiteEngine;
|
||||
|
||||
beforeAll(async () => {
|
||||
engine = new PGLiteEngine();
|
||||
await engine.connect({});
|
||||
await engine.initSchema();
|
||||
});
|
||||
|
||||
afterAll(async () => {
|
||||
await engine.disconnect();
|
||||
});
|
||||
|
||||
beforeEach(async () => {
|
||||
await resetPgliteState(engine);
|
||||
});
|
||||
|
||||
async function insertPage(opts: {
|
||||
slug: string;
|
||||
type: string;
|
||||
title: string;
|
||||
effectiveDate?: string;
|
||||
legacyType?: string;
|
||||
}): Promise<number> {
|
||||
const frontmatterLiteral = opts.legacyType
|
||||
? `'{"legacy_type": "${opts.legacyType}"}'::jsonb`
|
||||
: `'{}'::jsonb`;
|
||||
const rows = await engine.executeRaw<{ id: number }>(
|
||||
`INSERT INTO pages (slug, source_id, type, title, compiled_truth, timeline, effective_date, frontmatter)
|
||||
VALUES ($1, 'default', $2, $3, '', '', $4, ${frontmatterLiteral})
|
||||
RETURNING id`,
|
||||
[opts.slug, opts.type, opts.title, opts.effectiveDate ?? null],
|
||||
);
|
||||
return rows[0]!.id;
|
||||
}
|
||||
|
||||
describe('extractTimelineFromMeetings — legacy_type fallback (#2109)', () => {
|
||||
it('scans pages retyped to note with legacy_type=meeting and walks their attended edges', async () => {
|
||||
const meetingId = await insertPage({
|
||||
slug: 'meetings/2026-01-05',
|
||||
type: 'note', // post-unify-types shape on a gbrain-base-v2 brain
|
||||
legacyType: 'meeting',
|
||||
title: 'Weekly sync',
|
||||
effectiveDate: '2026-01-05',
|
||||
});
|
||||
const personId = await insertPage({
|
||||
slug: 'people/alice-example',
|
||||
type: 'person',
|
||||
title: 'Alice Example',
|
||||
});
|
||||
await engine.executeRaw(
|
||||
`INSERT INTO links (from_page_id, to_page_id, link_type) VALUES ($1, $2, 'attended')`,
|
||||
[meetingId, personId],
|
||||
);
|
||||
|
||||
const result = await extractTimelineFromMeetings(engine);
|
||||
expect(result.meetings_scanned).toBe(1);
|
||||
expect(result.entries_created).toBe(1);
|
||||
expect(result.entities_touched).toBe(1);
|
||||
expect(result.batch_errors).toBe(0);
|
||||
});
|
||||
|
||||
it('still scans pre-unify pages with type=meeting (v1 behavior preserved)', async () => {
|
||||
const meetingId = await insertPage({
|
||||
slug: 'meetings/2026-02-01',
|
||||
type: 'meeting',
|
||||
title: 'Board prep',
|
||||
effectiveDate: '2026-02-01',
|
||||
});
|
||||
const personId = await insertPage({
|
||||
slug: 'people/charlie-example',
|
||||
type: 'person',
|
||||
title: 'Charlie Example',
|
||||
});
|
||||
await engine.executeRaw(
|
||||
`INSERT INTO links (from_page_id, to_page_id, link_type) VALUES ($1, $2, 'attended')`,
|
||||
[meetingId, personId],
|
||||
);
|
||||
|
||||
const result = await extractTimelineFromMeetings(engine);
|
||||
expect(result.meetings_scanned).toBe(1);
|
||||
expect(result.entries_created).toBe(1);
|
||||
});
|
||||
|
||||
it('does not scan unrelated note pages without legacy_type=meeting', async () => {
|
||||
await insertPage({
|
||||
slug: 'notes/random',
|
||||
type: 'note',
|
||||
title: 'Random note',
|
||||
effectiveDate: '2026-03-01',
|
||||
});
|
||||
const result = await extractTimelineFromMeetings(engine);
|
||||
expect(result.meetings_scanned).toBe(0);
|
||||
expect(result.entries_created).toBe(0);
|
||||
});
|
||||
});
|
||||
@@ -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 |');
|
||||
});
|
||||
});
|
||||
@@ -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.
|
||||
|
||||
@@ -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 () => {
|
||||
|
||||
@@ -152,6 +152,19 @@ describe('list_schema_packs', () => {
|
||||
expect(result.installed).toContain('mine');
|
||||
});
|
||||
});
|
||||
|
||||
it('reports the full bundled registry, not a hand-copied subset (#1726)', async () => {
|
||||
await withEnv({ GBRAIN_HOME: tmpDir }, async () => {
|
||||
const { BUNDLED_PACKS } = await import('../src/core/schema-pack/load-active.ts');
|
||||
const result = await operationsByName.list_schema_packs!.handler(ctxOf(), {}) as { bundled: string[] };
|
||||
expect(result.bundled.slice().sort()).toEqual([...BUNDLED_PACKS].sort());
|
||||
// The lens packs that declare extract_atoms/synthesize_concepts phases
|
||||
// were the ones dropped by the frozen 2-pack literal.
|
||||
for (const name of ['gbrain-creator', 'gbrain-everything', 'gbrain-base-v2']) {
|
||||
expect(result.bundled).toContain(name);
|
||||
}
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
// ── schema_stats ───────────────────────────────────────────────────────
|
||||
|
||||
@@ -0,0 +1,40 @@
|
||||
// #2117 — gbrain-base-v2 shipped with no `phases:` declaration and zero
|
||||
// link_types[].inference regexes, so extract_atoms was silently pack-gated
|
||||
// off and extract-ner returned pack_unavailable on the bundled default pack.
|
||||
// These assertions fail against the pre-fix yaml.
|
||||
|
||||
import { describe, expect, it } from 'bun:test';
|
||||
import { join } from 'node:path';
|
||||
import { loadPackFromFile } from '../src/core/schema-pack/loader.ts';
|
||||
import { linkTypesUndeclared } from '../src/core/schema-pack/lint-rules.ts';
|
||||
|
||||
const V2_PATH = join(import.meta.dir, '..', 'src', 'core', 'schema-pack', 'base', 'gbrain-base-v2.yaml');
|
||||
|
||||
describe('gbrain-base-v2 capability parity (#2117)', () => {
|
||||
const manifest = loadPackFromFile(V2_PATH);
|
||||
|
||||
it('declares the extract_atoms cycle phase', () => {
|
||||
expect(manifest.phases ?? []).toContain('extract_atoms');
|
||||
});
|
||||
|
||||
it('ships at least one link_type inference regex so extract-ner is not pack_unavailable', () => {
|
||||
// Mirrors the extract-ner hasRegex predicate exactly.
|
||||
const hasRegex = manifest.link_types.some(
|
||||
(lt) => lt.inference && typeof lt.inference === 'object' && 'regex' in lt.inference,
|
||||
);
|
||||
expect(hasRegex).toBe(true);
|
||||
});
|
||||
|
||||
it('ports the v1 inference verbs it declares link types for', () => {
|
||||
const withRegex = manifest.link_types
|
||||
.filter((lt) => lt.inference?.regex)
|
||||
.map((lt) => lt.name)
|
||||
.sort();
|
||||
expect(withRegex).toEqual(['founded', 'invested_in', 'works_at']);
|
||||
});
|
||||
|
||||
it('inference rules pass the undeclared-page-type lint (no meeting-bound inference)', async () => {
|
||||
const issues = await linkTypesUndeclared(manifest);
|
||||
expect(issues).toEqual([]);
|
||||
});
|
||||
});
|
||||
Reference in New Issue
Block a user