mirror of
https://github.com/garrytan/gbrain.git
synced 2026-08-17 10:22:34 +00:00
Compare commits
3
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
52fffc7ecc | ||
|
|
039b97df36 | ||
|
|
2bb3424863 |
+12
-1
@@ -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)
|
||||
|
||||
+3
-22
@@ -433,10 +433,7 @@ export async function extractLinksFromFile(
|
||||
async resolve(name: string, dirHint?: string | string[]): Promise<string | null> {
|
||||
if (!name) return null;
|
||||
const trimmed = name.trim();
|
||||
// Same broadened slug-shape as makeResolver step 1: accepts
|
||||
// digit-leading folders (`90-people/nicolai`) and nested paths.
|
||||
// Exact Set membership guards it — no false positives.
|
||||
if (/\//.test(trimmed) && /^[a-z0-9][a-z0-9/_-]*$/.test(trimmed) && allSlugs.has(trimmed)) {
|
||||
if (/^[a-z][a-z0-9-]*\/[a-z0-9][a-z0-9-]*$/.test(trimmed) && allSlugs.has(trimmed)) {
|
||||
return trimmed;
|
||||
}
|
||||
const hints = Array.isArray(dirHint) ? dirHint : (dirHint ? [dirHint] : []);
|
||||
@@ -585,17 +582,6 @@ export interface ExtractOpts {
|
||||
* before (single-'default'-source brains unaffected).
|
||||
*/
|
||||
sourceId?: string;
|
||||
/**
|
||||
* v0.42 — also extract frontmatter links on the incremental (slugs) path.
|
||||
* `extractForSlugs` extracts BODY links only by default; set this true to also
|
||||
* parse each changed page's frontmatter so `sources:`/`related:` edges stay fresh
|
||||
* when YAML is edited externally and synced in. Applied PER changed page, so the
|
||||
* incremental walk stays bounded (no switch to a full DB scan). Only honored on
|
||||
* the incremental path (`slugs` defined); the full-walk path already covers
|
||||
* frontmatter via its own dispatch. Gated upstream by the config key
|
||||
* `autopilot.incremental_extract_include_frontmatter` (default off).
|
||||
*/
|
||||
includeFrontmatter?: boolean;
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -634,7 +620,7 @@ export async function runExtractCore(engine: BrainEngine, opts: ExtractOpts): Pr
|
||||
// Nothing changed — skip entirely.
|
||||
return result;
|
||||
}
|
||||
const r = await extractForSlugs(engine, opts.dir, opts.slugs, opts.mode, dryRun, jsonMode, workers, opts.signal, opts.sourceId, opts.includeFrontmatter);
|
||||
const r = await extractForSlugs(engine, opts.dir, opts.slugs, opts.mode, dryRun, jsonMode, workers, opts.signal, opts.sourceId);
|
||||
result.links_created = r.links_created;
|
||||
result.timeline_entries_created = r.timeline_created;
|
||||
result.pages_processed = r.pages;
|
||||
@@ -1025,11 +1011,6 @@ async function extractForSlugs(
|
||||
signal?: AbortSignal,
|
||||
// #1747/#1503: stamp resolved brain source id on batch rows (see ExtractOpts.sourceId).
|
||||
sourceId?: string,
|
||||
// v0.42: when true, also extract frontmatter links per changed page so
|
||||
// externally-edited YAML (`sources:`/`related:`) stays fresh on the cycle.
|
||||
// Default false preserves the body-only incremental behavior. Gated upstream
|
||||
// by `autopilot.incremental_extract_include_frontmatter`.
|
||||
includeFrontmatter: boolean = false,
|
||||
): Promise<{ links_created: number; timeline_created: number; pages: number }> {
|
||||
// Build the full slug set for link resolution (fast: just readdir, no file reads)
|
||||
const allFiles = walkMarkdownFiles(brainDir);
|
||||
@@ -1104,7 +1085,7 @@ async function extractForSlugs(
|
||||
const content = readFileSync(fullPath, 'utf-8');
|
||||
|
||||
if (doLinks) {
|
||||
const links = await extractLinksFromFile(content, relPath, allSlugs, { globalBasename, includeFrontmatter });
|
||||
const links = await extractLinksFromFile(content, relPath, allSlugs, { globalBasename });
|
||||
for (const link of links) {
|
||||
if (dryRun) {
|
||||
if (!jsonMode) console.log(` ${link.from_slug} → ${link.to_slug} (${link.link_type})`);
|
||||
|
||||
@@ -0,0 +1,48 @@
|
||||
/**
|
||||
* gbrain facts — fact-store maintenance surface (#1867).
|
||||
*
|
||||
* `fence-backfill` re-runs the v0_32_2 fence-backfill phase on demand.
|
||||
* Remote `extract_facts` deposits that predate the fence-write backstop
|
||||
* (and any legacy DB-only insert) leave `row_num IS NULL` rows that the
|
||||
* cycle extract_facts guard refuses to reconcile past — previously the
|
||||
* only remedy was the one-shot v0_32_2 migration, which the ledger marks
|
||||
* complete and never re-runs. The phase is idempotent (only touches
|
||||
* `row_num IS NULL` rows), so exposing it as a command is safe to re-run
|
||||
* any time the backlog reappears.
|
||||
*/
|
||||
import type { BrainEngine } from '../core/engine.ts';
|
||||
import { setCliExitVerdict } from '../core/cli-force-exit.ts';
|
||||
import { phaseBFenceFacts } from './migrations/v0_32_2.ts';
|
||||
|
||||
function printHelp(): void {
|
||||
process.stderr.write(
|
||||
`Usage: gbrain facts fence-backfill [--dry-run]\n\n` +
|
||||
`Fence-backfill: appends every legacy fact row (row_num IS NULL) to its\n` +
|
||||
`entity page's \`## Facts\` fence and stamps row_num + source_markdown_slug\n` +
|
||||
`back onto the DB row. Idempotent — re-runs only pick up rows still\n` +
|
||||
`missing a fence assignment. Clears the backlog that makes the cycle's\n` +
|
||||
`extract_facts phase skip fence→DB reconciliation.\n\n` +
|
||||
` --dry-run report what would be fenced; no FS or DB writes\n`,
|
||||
);
|
||||
}
|
||||
|
||||
export async function runFactsCommand(engine: BrainEngine, args: string[]): Promise<void> {
|
||||
const sub = args[0];
|
||||
if (!sub || sub === '--help' || sub === '-h') {
|
||||
printHelp();
|
||||
return;
|
||||
}
|
||||
if (sub !== 'fence-backfill') {
|
||||
process.stderr.write(`Unknown facts subcommand: ${sub}\n`);
|
||||
printHelp();
|
||||
setCliExitVerdict(1);
|
||||
return;
|
||||
}
|
||||
|
||||
const dryRun = args.includes('--dry-run');
|
||||
const result = await phaseBFenceFacts(engine, { dryRun });
|
||||
process.stderr.write(
|
||||
`fence-backfill: ${result.status}${result.detail ? ` — ${result.detail}` : ''}\n`,
|
||||
);
|
||||
if (result.status === 'failed') setCliExitVerdict(1);
|
||||
}
|
||||
@@ -39,6 +39,7 @@ import type { BrainEngine } from '../../core/engine.ts';
|
||||
import { loadConfig, toEngineConfig } from '../../core/config.ts';
|
||||
import { createEngine } from '../../core/engine-factory.ts';
|
||||
import { upsertFactRow, parseFactsFence } from '../../core/facts-fence.ts';
|
||||
import { resolvePageFilePath } from '../../core/markdown.ts';
|
||||
|
||||
let testEngineOverride: BrainEngine | null = null;
|
||||
export function __setTestEngineOverride(engine: BrainEngine | null): void {
|
||||
@@ -148,9 +149,16 @@ function isLocalPathDirty(localPath: string): boolean {
|
||||
}
|
||||
}
|
||||
|
||||
async function phaseBFenceFacts(
|
||||
/**
|
||||
* Exported (not just via `__testing`) because `gbrain facts fence-backfill`
|
||||
* (#1867) re-runs this phase on demand: remote `extract_facts` deposits that
|
||||
* predate the fence-write backstop leave row_num-NULL rows the cycle guard
|
||||
* refuses to reconcile past. The phase is idempotent (only touches
|
||||
* `row_num IS NULL` rows), so re-running is always safe.
|
||||
*/
|
||||
export async function phaseBFenceFacts(
|
||||
engine: BrainEngine | null,
|
||||
opts: OrchestratorOpts,
|
||||
opts: Pick<OrchestratorOpts, 'dryRun'>,
|
||||
): Promise<OrchestratorPhaseResult> {
|
||||
if (opts.dryRun) {
|
||||
// Dry-run: report what WOULD happen without touching FS or DB.
|
||||
@@ -238,7 +246,11 @@ async function phaseBFenceFacts(
|
||||
for (const [key, group] of groups) {
|
||||
const [sourceId, entitySlug] = key.split('\0');
|
||||
const localPath = localPathById.get(sourceId)!;
|
||||
const filePath = join(localPath, `${entitySlug}.md`);
|
||||
// resolvePageFilePath, NOT a bare join — non-default sources fence
|
||||
// into `<local_path>/.sources/<id>/<slug>.md`, the same path the
|
||||
// fence-write backstop and put_page write-through compute. A bare
|
||||
// join here diverges fence and DB for non-default sources (#2044).
|
||||
const filePath = resolvePageFilePath(localPath, entitySlug, sourceId);
|
||||
const tmpPath = `${filePath}.tmp`;
|
||||
|
||||
try {
|
||||
@@ -269,6 +281,21 @@ async function phaseBFenceFacts(
|
||||
const existingFence = parseFactsFence(body);
|
||||
const existingKeySet = new Set(existingFence.facts.map(f => `${f.claim}\0${f.source ?? ''}`));
|
||||
|
||||
// Seed appended row_nums from MAX(fence max, DB max) — same #2044
|
||||
// divergence guard as writeFactsToFence. When the fence at the
|
||||
// resolved path is missing/behind but the DB already holds stamped
|
||||
// rows for this slug (legacy wrong-path fence writes), fence-max+1
|
||||
// collides with idx_facts_fence_key on the post-rename UPDATE,
|
||||
// failing the page and leaving fence and DB disagreeing.
|
||||
const dbMaxRows = await engine.executeRaw<{ max: number | string | null }>(
|
||||
`SELECT MAX(row_num) AS max FROM facts
|
||||
WHERE source_id = $1 AND source_markdown_slug = $2`,
|
||||
[sourceId, entitySlug],
|
||||
);
|
||||
const dbMaxRowNum = Number(dbMaxRows[0]?.max ?? 0) || 0;
|
||||
const fenceMaxRowNum = existingFence.facts.reduce((m, f) => Math.max(m, f.rowNum), 0);
|
||||
let nextRowNum = Math.max(fenceMaxRowNum, dbMaxRowNum) + 1;
|
||||
|
||||
const assignments: Array<{ id: string; row_num: number }> = [];
|
||||
for (const row of group) {
|
||||
const key = `${row.fact}\0${row.source ?? ''}`;
|
||||
@@ -291,6 +318,7 @@ async function phaseBFenceFacts(
|
||||
.toISOString().slice(0, 10)
|
||||
: undefined;
|
||||
const { body: updated, rowNum } = upsertFactRow(body, {
|
||||
rowNum: nextRowNum++,
|
||||
claim: row.fact,
|
||||
kind: row.kind,
|
||||
confidence: row.confidence,
|
||||
@@ -381,7 +409,7 @@ async function phaseCVerify(
|
||||
for (const g of groups) {
|
||||
const localPath = localPathById.get(g.source_id);
|
||||
if (!localPath) continue;
|
||||
const filePath = join(localPath, `${g.source_markdown_slug}.md`);
|
||||
const filePath = resolvePageFilePath(localPath, g.source_markdown_slug, g.source_id);
|
||||
if (!existsSync(filePath)) {
|
||||
mismatches.push(`${g.source_markdown_slug} (file missing)`);
|
||||
continue;
|
||||
|
||||
@@ -121,18 +121,6 @@ export interface GBrainConfig {
|
||||
/** Daily spend cap (USD); bounds drains/day = floor(cap / ~$0.30). Default 2.0. */
|
||||
max_usd_per_day?: number;
|
||||
};
|
||||
/**
|
||||
* v0.42 — keep frontmatter links fresh on the incremental cycle. The cycle's
|
||||
* extract phase re-extracts only the slugs a sync changed, but `extractForSlugs`
|
||||
* extracts BODY links only — frontmatter (`sources:`/`related:` etc.) link edges
|
||||
* silently drift stale when a page's YAML is edited externally and synced in.
|
||||
* Set true to also extract frontmatter links per changed page each cycle, keeping
|
||||
* externally-edited YAML edges fresh without a full rescan. Default false
|
||||
* (preserves current behavior). Read via the file/env/DB plane in the cycle's
|
||||
* extract dispatch. Disable/enable with
|
||||
* `gbrain config set autopilot.incremental_extract_include_frontmatter <bool>`.
|
||||
*/
|
||||
incremental_extract_include_frontmatter?: boolean;
|
||||
};
|
||||
eval?: {
|
||||
/** false disables capture entirely. Defaults to true. */
|
||||
|
||||
@@ -996,21 +996,6 @@ async function runPhaseExtract(
|
||||
): Promise<PhaseResult> {
|
||||
try {
|
||||
const { runExtractCore } = await import('../commands/extract.ts');
|
||||
const { loadConfig } = await import('./config.ts');
|
||||
// Default off: the incremental cycle extracts body links only unless the
|
||||
// operator opts in to keeping externally-edited frontmatter links fresh too.
|
||||
// Both planes, file wins (env > file > DB precedence, per loadConfigWithEngine):
|
||||
// `gbrain config set autopilot.incremental_extract_include_frontmatter true`
|
||||
// writes the DB plane (engine.setConfig), so a file-plane-only read here
|
||||
// would make the documented enable command a silent no-op (#2120 class).
|
||||
const fileVal = loadConfig()?.autopilot?.incremental_extract_include_frontmatter;
|
||||
let includeFrontmatter = fileVal === true;
|
||||
if (fileVal === undefined) {
|
||||
try {
|
||||
includeFrontmatter =
|
||||
(await engine.getConfig('autopilot.incremental_extract_include_frontmatter')) === 'true';
|
||||
} catch { /* config table unreadable → default off */ }
|
||||
}
|
||||
// Extract is read-mostly against the filesystem + write to links table.
|
||||
// Honor dryRun by skipping with a 'skipped' entry: extract doesn't have
|
||||
// a clean dry-run mode today and runCycle should be honest about it.
|
||||
@@ -1031,7 +1016,6 @@ async function runPhaseExtract(
|
||||
slugs: changedSlugs, // undefined = full walk (first run / manual)
|
||||
signal,
|
||||
sourceId,
|
||||
includeFrontmatter, // honored on the incremental (slugs) path only
|
||||
});
|
||||
const linksCreated = result?.links_created ?? 0;
|
||||
const timelineCreated = result?.timeline_entries_created ?? 0;
|
||||
|
||||
@@ -176,9 +176,11 @@ export async function runExtractFacts(
|
||||
if (legacyCount > 0) {
|
||||
result.guardTriggered = true;
|
||||
result.warnings.push(
|
||||
`extract_facts: ${legacyCount} legacy v0.31 fact rows pending fence backfill. ` +
|
||||
`Run \`gbrain apply-migrations --yes\` to complete v0_32_2 before this phase ` +
|
||||
`can safely reconcile fence → DB.`,
|
||||
`extract_facts: ${legacyCount} legacy fact rows pending fence backfill ` +
|
||||
`(row_num IS NULL — v0.31 rows or remote extract_facts deposits that ` +
|
||||
`predate the fence backstop). Run \`gbrain facts fence-backfill\` ` +
|
||||
`(idempotent, re-runnable) before this phase can safely reconcile ` +
|
||||
`fence → DB.`,
|
||||
);
|
||||
return result;
|
||||
}
|
||||
|
||||
+7
-6
@@ -1739,13 +1739,14 @@ export interface BrainEngine {
|
||||
* single-row supersede flow because fence reconciliation is the canonical
|
||||
* source-of-truth direction, not the consolidator path.
|
||||
*
|
||||
* Insertion is atomic per call: all rows commit in a single transaction
|
||||
* or none commit (the transaction rolls back on any constraint
|
||||
* violation, e.g. the v51 partial UNIQUE index on
|
||||
* `(source_id, source_markdown_slug, row_num)`).
|
||||
* Insertion runs in a single transaction. A collision on the v51
|
||||
* partial UNIQUE index `(source_id, source_markdown_slug, row_num)`
|
||||
* skips ONLY that row (ON CONFLICT DO NOTHING, #2044) — the rest of
|
||||
* the batch still commits, so a redundant deposit against an
|
||||
* already-indexed fence row is idempotent instead of a hard failure.
|
||||
*
|
||||
* Returns the inserted ids in input-order so callers can correlate
|
||||
* fence-row → DB-id without a separate lookup.
|
||||
* Returns the inserted ids in input-order (colliding rows omitted) so
|
||||
* callers can correlate fence-row → DB-id without a separate lookup.
|
||||
*/
|
||||
insertFacts(
|
||||
rows: Array<NewFact & { row_num: number; source_markdown_slug: string }>,
|
||||
|
||||
@@ -218,11 +218,27 @@ export async function writeFactsToFence(
|
||||
}
|
||||
|
||||
// 2. Upsert each fact onto the fence in input order. row_num
|
||||
// monotonically increases (max-existing + 1 per call, append-only).
|
||||
// monotonically increases, append-only, seeded from the MAX of
|
||||
// the fence and the DB index (#2044): when fence and DB have
|
||||
// diverged (e.g. legacy writes that stamped DB rows against a
|
||||
// fence at a path this code no longer reads), fence-max+1 can
|
||||
// collide with an existing DB row_num, tripping
|
||||
// idx_facts_fence_key and rolling back the whole batch.
|
||||
const dbMaxRows = await engine.executeRaw<{ max: number | string | null }>(
|
||||
`SELECT MAX(row_num) AS max FROM facts
|
||||
WHERE source_id = $1 AND source_markdown_slug = $2`,
|
||||
[target.sourceId, target.slug],
|
||||
);
|
||||
const dbMaxRowNum = Number(dbMaxRows[0]?.max ?? 0) || 0;
|
||||
const fenceMaxRowNum = parseFactsFence(body).facts
|
||||
.reduce((m, f) => Math.max(m, f.rowNum), 0);
|
||||
let nextRowNum = Math.max(fenceMaxRowNum, dbMaxRowNum) + 1;
|
||||
|
||||
const assignedRowNums: number[] = [];
|
||||
for (const f of facts) {
|
||||
const validFromStr = (f.validFrom ?? new Date()).toISOString().slice(0, 10);
|
||||
const { body: updated, rowNum } = upsertFactRow(body, {
|
||||
rowNum: nextRowNum++,
|
||||
claim: f.fact,
|
||||
kind: (f.kind ?? 'fact') as 'fact' | 'event' | 'preference' | 'commitment' | 'belief',
|
||||
confidence: f.confidence ?? 1.0,
|
||||
|
||||
@@ -942,17 +942,8 @@ export function makeResolver(
|
||||
|
||||
const hints = Array.isArray(dirHint) ? dirHint : (dirHint ? [dirHint] : []);
|
||||
|
||||
// Step 1: already a slug? Try an exact page lookup for any slug-shaped
|
||||
// value (contains '/', slug charset). Broadened beyond the original
|
||||
// single-segment lowercase-leading form (`^[a-z][a-z0-9-]*\/[a-z0-9]...`)
|
||||
// to also accept digit-leading folders (`90-people/nicolai`,
|
||||
// `01-trading/...`) and nested paths (`a/b/c`) — common in PARA-numbered
|
||||
// vaults. This is an EXACT getPage match only — no fuzzy — so it never
|
||||
// produces a false positive; a non-existent slug just falls through to
|
||||
// the steps below. Fixes frontmatter `related: [[dir/slug]]` values
|
||||
// (unwrapped by unwrapWikilink) that name a real page the strict regex
|
||||
// could not reach and whose full-path fuzzy score is below threshold.
|
||||
if (/\//.test(trimmed) && /^[a-z0-9][a-z0-9/_-]*$/.test(trimmed)) {
|
||||
// Step 1: already a slug? (dir/name shape, lowercase, hyphenated)
|
||||
if (/^[a-z][a-z0-9-]*\/[a-z0-9][a-z0-9-]*$/.test(trimmed)) {
|
||||
const page = await engine.getPage(trimmed);
|
||||
if (page) {
|
||||
cache.set(cacheKey, trimmed);
|
||||
@@ -1012,25 +1003,6 @@ export function makeResolver(
|
||||
|
||||
// ─── Frontmatter extractor ──────────────────────────────────────
|
||||
|
||||
/**
|
||||
* Unwrap an Obsidian `[[wikilink]]` frontmatter value to its bare link
|
||||
* target so the resolver (which expects bare titles / dir slugs) can match
|
||||
* it. Mainstream Obsidian authors frontmatter links as `related: ["[[Page]]"]`;
|
||||
* without this, the resolver treats the brackets as part of the value and a
|
||||
* `[[90-people/nicolai]]` is normalized into `90peoplenicolai`, so it never
|
||||
* resolves. Strips a trailing `|alias`, `#heading`, or `^block` suffix — the
|
||||
* link target only. The regex is anchored to a wholly-wrapped value
|
||||
* (`^\s*\[\[…\]\]\s*$`), so bare titles and any value not fully wrapped pass
|
||||
* through unchanged and existing behavior is preserved exactly.
|
||||
*/
|
||||
export function unwrapWikilink(value: string): string {
|
||||
const match = /^\s*\[\[(.+?)\]\]\s*$/.exec(value);
|
||||
if (!match) return value;
|
||||
// Take the link target: drop |alias, then #heading / ^block suffixes.
|
||||
const target = match[1].split('|')[0].split('#')[0].split('^')[0];
|
||||
return target.trim();
|
||||
}
|
||||
|
||||
export interface UnresolvedFrontmatterRef {
|
||||
/** The frontmatter field name. */
|
||||
field: string;
|
||||
@@ -1088,12 +1060,7 @@ export async function extractFrontmatterLinks(
|
||||
}
|
||||
if (!name) continue; // skip numbers, nulls, malformed objects
|
||||
|
||||
// Accept Obsidian `[[wikilink]]` values in frontmatter link fields by
|
||||
// unwrapping to the bare target before resolution. Bare titles pass
|
||||
// through unchanged; the original `name` is preserved for the
|
||||
// unresolved report and edge context.
|
||||
const linkTarget = unwrapWikilink(name);
|
||||
const resolved = await resolver.resolve(linkTarget, mapping.dirHint);
|
||||
const resolved = await resolver.resolve(name, mapping.dirHint);
|
||||
if (!resolved) {
|
||||
unresolved.push({ field, name });
|
||||
continue;
|
||||
|
||||
@@ -4102,11 +4102,13 @@ export class PGLiteEngine implements BrainEngine {
|
||||
): Promise<{ inserted: number; ids: number[] }> {
|
||||
if (rows.length === 0) return { inserted: 0, ids: [] };
|
||||
|
||||
// Single transaction so the v51 partial UNIQUE index can roll back the
|
||||
// whole batch on constraint violation. Per-row INSERTs (not multi-row
|
||||
// VALUES) keep the embedding-vs-no-embedding branching readable; batch
|
||||
// sizes are small (5-30 rows per page in practice) so the loop overhead
|
||||
// is negligible vs the embedding compute cost.
|
||||
// Single transaction; per-row INSERTs (not multi-row VALUES) keep the
|
||||
// embedding-vs-no-embedding branching readable; batch sizes are small
|
||||
// (5-30 rows per page in practice) so the loop overhead is negligible
|
||||
// vs the embedding compute cost. #2044: ON CONFLICT DO NOTHING on the
|
||||
// v51 partial UNIQUE index makes a residual fence/DB row_num collision
|
||||
// skip that row instead of rolling back the whole batch (parity with
|
||||
// postgres-engine.ts).
|
||||
const ids = await this.db.transaction(async (tx) => {
|
||||
const out: number[] = [];
|
||||
for (const input of rows) {
|
||||
@@ -4149,7 +4151,11 @@ export class PGLiteEngine implements BrainEngine {
|
||||
$14, $15,
|
||||
$16, $17, $18, $19,
|
||||
$20
|
||||
) RETURNING id`
|
||||
)
|
||||
ON CONFLICT (source_id, source_markdown_slug, row_num)
|
||||
WHERE row_num IS NOT NULL
|
||||
DO NOTHING
|
||||
RETURNING id`
|
||||
: `INSERT INTO facts (
|
||||
source_id, entity_slug, fact, kind, visibility, notability, context,
|
||||
valid_from, valid_until, source, source_session, confidence,
|
||||
@@ -4163,12 +4169,16 @@ export class PGLiteEngine implements BrainEngine {
|
||||
$15, $16,
|
||||
$17, $18, $19, $20,
|
||||
$21
|
||||
) RETURNING id`,
|
||||
)
|
||||
ON CONFLICT (source_id, source_markdown_slug, row_num)
|
||||
WHERE row_num IS NOT NULL
|
||||
DO NOTHING
|
||||
RETURNING id`,
|
||||
embedStr === null
|
||||
? [ctx.source_id, entitySlug, input.fact, kind, visibility, notability, context, validFrom, validUntil, input.source, sourceSession, confidence, embeddedAt, input.row_num, input.source_markdown_slug, claimMetric, claimValue, claimUnit, claimPeriod, eventType]
|
||||
: [ctx.source_id, entitySlug, input.fact, kind, visibility, notability, context, validFrom, validUntil, input.source, sourceSession, confidence, embedStr, embeddedAt, input.row_num, input.source_markdown_slug, claimMetric, claimValue, claimUnit, claimPeriod, eventType],
|
||||
);
|
||||
out.push(ins.rows[0].id);
|
||||
if (ins.rows[0]) out.push(ins.rows[0].id);
|
||||
}
|
||||
return out;
|
||||
});
|
||||
|
||||
@@ -4302,10 +4302,12 @@ export class PostgresEngine implements BrainEngine {
|
||||
// ONCE per process so the cast matches the actual column type
|
||||
// (halfvec vs vector). The probe is cached after first call.
|
||||
const castSuffix = await this.resolveFactsEmbeddingCast();
|
||||
// Single transaction so the v51 partial UNIQUE index can roll back
|
||||
// the whole batch on constraint violation. Per-row INSERTs (not
|
||||
// multi-row VALUES) keep the embedding-vs-no-embedding branching
|
||||
// readable; batch sizes are small (5-30 rows per page in practice).
|
||||
// Single transaction; per-row INSERTs (not multi-row VALUES) keep the
|
||||
// embedding-vs-no-embedding branching readable; batch sizes are small
|
||||
// (5-30 rows per page in practice). #2044: ON CONFLICT DO NOTHING on
|
||||
// the v51 partial UNIQUE index makes a residual fence/DB row_num
|
||||
// collision skip that row instead of rolling back the whole batch —
|
||||
// the fence stays system-of-record and reconciliation catches up.
|
||||
// No supersede flow in this path — fence reconciliation is the
|
||||
// canonical source-of-truth direction, not the consolidator path.
|
||||
const ids = await sql.begin(async (tx) => {
|
||||
@@ -4346,9 +4348,13 @@ export class PostgresEngine implements BrainEngine {
|
||||
${input.row_num}, ${input.source_markdown_slug},
|
||||
${claimMetric}, ${claimValue}, ${claimUnit}, ${claimPeriod},
|
||||
${eventType}
|
||||
) RETURNING id
|
||||
)
|
||||
ON CONFLICT (source_id, source_markdown_slug, row_num)
|
||||
WHERE row_num IS NOT NULL
|
||||
DO NOTHING
|
||||
RETURNING id
|
||||
`;
|
||||
out.push(Number(ins[0].id));
|
||||
if (ins[0]) out.push(Number(ins[0].id));
|
||||
}
|
||||
return out;
|
||||
});
|
||||
|
||||
@@ -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
|
||||
|
||||
@@ -191,37 +191,3 @@ describe('runExtractCore — incremental cycle path (#417)', () => {
|
||||
expect(result.links_created).toBeGreaterThan(0);
|
||||
});
|
||||
});
|
||||
describe('runExtractCore — incremental frontmatter gate (includeFrontmatter)', () => {
|
||||
// alice has a `source:` frontmatter edge but NO body links. The incremental
|
||||
// path extracts body links only by default, so the frontmatter edge is the
|
||||
// sole signal that distinguishes the gate off vs on.
|
||||
const aliceFm = '---\nsource: companies/acme-example\n---\n# alice';
|
||||
|
||||
test('9. default (flag omitted) does NOT extract frontmatter links on the incremental path', async () => {
|
||||
await seedPage('companies/acme-example', '# acme');
|
||||
await seedPage('people/alice-example', aliceFm);
|
||||
const result = await runExtractCore(engine as unknown as BrainEngine, {
|
||||
mode: 'all',
|
||||
dir: tempDir,
|
||||
slugs: ['people/alice-example'],
|
||||
});
|
||||
// alice's only potential edge is her frontmatter `source:`; with the gate off
|
||||
// it must not be extracted (preserves the body-only incremental behavior).
|
||||
expect(result.pages_processed).toBe(1);
|
||||
expect(result.links_created).toBe(0);
|
||||
});
|
||||
|
||||
test('10. includeFrontmatter: true extracts the frontmatter link on the incremental path', async () => {
|
||||
await seedPage('companies/acme-example', '# acme');
|
||||
await seedPage('people/alice-example', aliceFm);
|
||||
const result = await runExtractCore(engine as unknown as BrainEngine, {
|
||||
mode: 'all',
|
||||
dir: tempDir,
|
||||
slugs: ['people/alice-example'],
|
||||
includeFrontmatter: true,
|
||||
});
|
||||
// Same page, gate on → the `source:` frontmatter edge is now extracted.
|
||||
expect(result.pages_processed).toBe(1);
|
||||
expect(result.links_created).toBeGreaterThan(0);
|
||||
});
|
||||
});
|
||||
|
||||
@@ -76,18 +76,6 @@ describe('extractLinksFromFile', () => {
|
||||
}
|
||||
});
|
||||
|
||||
it('resolves wrapped [[wikilink]] digit-leading slug-path in frontmatter (fs resolver, broadened step 1)', async () => {
|
||||
// Same bug class as makeResolver step 1 (#1983): the fs resolver's strict
|
||||
// `^[a-z]…` slug regex rejected digit-leading / nested paths, so a PARA-vault
|
||||
// `related: "[[90-people/nicolai]]"` never resolved even though the page exists.
|
||||
const content = '---\nrelated: "[[90-people/nicolai]]"\ntype: concept\n---\nContent.';
|
||||
const allSlugs = new Set(['wiki/note', '90-people/nicolai']);
|
||||
const links = await extractLinksFromFile(content, 'wiki/note.md', allSlugs, { includeFrontmatter: true });
|
||||
const related = links.filter(l => l.link_type === 'related_to');
|
||||
expect(related).toHaveLength(1);
|
||||
expect(related[0].to_slug).toBe('90-people/nicolai');
|
||||
});
|
||||
|
||||
it('frontmatter extraction is default OFF (back-compat)', async () => {
|
||||
// Without includeFrontmatter, fs-source no longer auto-extracts frontmatter.
|
||||
// Matches db-source behavior. User opts in with --include-frontmatter flag.
|
||||
|
||||
@@ -0,0 +1,133 @@
|
||||
/**
|
||||
* #1867 — `gbrain facts fence-backfill` command tests.
|
||||
*
|
||||
* The command re-runs the (idempotent) v0_32_2 phase B on demand so
|
||||
* row_num-NULL backlogs — remote extract_facts deposits that predate
|
||||
* the fence-write backstop — can be cleared without re-running the
|
||||
* one-shot migration. Real PGLite + real tempdir filesystem.
|
||||
*/
|
||||
|
||||
import { describe, test, expect, beforeAll, afterAll, beforeEach } from 'bun:test';
|
||||
import { mkdtempSync, rmSync, existsSync, readFileSync } from 'node:fs';
|
||||
import { tmpdir } from 'node:os';
|
||||
import { join } from 'node:path';
|
||||
|
||||
import { PGLiteEngine } from '../src/core/pglite-engine.ts';
|
||||
import { runFactsCommand } from '../src/commands/facts.ts';
|
||||
import { phaseBFenceFacts } from '../src/commands/migrations/v0_32_2.ts';
|
||||
|
||||
let engine: PGLiteEngine;
|
||||
let brainDir: string;
|
||||
|
||||
beforeAll(async () => {
|
||||
engine = new PGLiteEngine();
|
||||
await engine.connect({});
|
||||
await engine.initSchema();
|
||||
});
|
||||
|
||||
afterAll(async () => {
|
||||
await engine.disconnect();
|
||||
try {
|
||||
if (brainDir) rmSync(brainDir, { recursive: true, force: true });
|
||||
} catch { /* best-effort */ }
|
||||
});
|
||||
|
||||
beforeEach(async () => {
|
||||
brainDir = mkdtempSync(join(tmpdir(), 'facts-backfill-cmd-test-'));
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
await (engine as any).db.query('DELETE FROM facts');
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
await (engine as any).db.query(
|
||||
`UPDATE sources SET local_path = $1 WHERE id = 'default'`,
|
||||
[brainDir],
|
||||
);
|
||||
});
|
||||
|
||||
async function seedLegacyFact(fact: string): Promise<void> {
|
||||
// The row_num-NULL shape a remote extract_facts deposit leaves behind
|
||||
// when it lands via the legacy DB-only path.
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
await (engine as any).db.query(
|
||||
`INSERT INTO facts (source_id, entity_slug, fact, kind, visibility, notability,
|
||||
valid_from, source, confidence)
|
||||
VALUES ('default', 'people/alice', $1, 'fact', 'private', 'medium',
|
||||
now(), 'mcp:extract_facts', 1.0)`,
|
||||
[fact],
|
||||
);
|
||||
}
|
||||
|
||||
describe('gbrain facts fence-backfill', () => {
|
||||
test('fences row_num-NULL rows and stamps the DB', async () => {
|
||||
await seedLegacyFact('Deposited remotely');
|
||||
|
||||
await runFactsCommand(engine, ['fence-backfill']);
|
||||
|
||||
// The fence exists on disk with the claim.
|
||||
const filePath = join(brainDir, 'people/alice.md');
|
||||
expect(existsSync(filePath)).toBe(true);
|
||||
expect(readFileSync(filePath, 'utf-8')).toContain('Deposited remotely');
|
||||
|
||||
// The backlog is cleared: no row_num-NULL rows remain.
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
const rows = await (engine as any).db.query(
|
||||
'SELECT row_num, source_markdown_slug FROM facts',
|
||||
);
|
||||
expect(rows.rows).toHaveLength(1);
|
||||
expect(rows.rows[0].row_num).toBe(1);
|
||||
expect(rows.rows[0].source_markdown_slug).toBe('people/alice');
|
||||
});
|
||||
|
||||
test('re-run is a no-op (idempotent)', async () => {
|
||||
await seedLegacyFact('Deposited remotely');
|
||||
await runFactsCommand(engine, ['fence-backfill']);
|
||||
await runFactsCommand(engine, ['fence-backfill']);
|
||||
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
const rows = await (engine as any).db.query('SELECT id FROM facts');
|
||||
expect(rows.rows).toHaveLength(1);
|
||||
const body = readFileSync(join(brainDir, 'people/alice.md'), 'utf-8');
|
||||
expect(body.match(/Deposited remotely/g)).toHaveLength(1);
|
||||
});
|
||||
|
||||
test('--dry-run reports without writing', async () => {
|
||||
await seedLegacyFact('Deposited remotely');
|
||||
await runFactsCommand(engine, ['fence-backfill', '--dry-run']);
|
||||
|
||||
expect(existsSync(join(brainDir, 'people/alice.md'))).toBe(false);
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
const rows = await (engine as any).db.query(
|
||||
'SELECT row_num FROM facts',
|
||||
);
|
||||
expect(rows.rows[0].row_num).toBeNull();
|
||||
});
|
||||
|
||||
test('diverged page: appends past the DB row_num max instead of colliding (#2044 class)', async () => {
|
||||
// The #2044 divergence shape the backfill must survive: the DB already
|
||||
// holds stamped rows 1..3 for the slug (legacy wrong-path fence write),
|
||||
// but the fence at the resolved path is missing. Fence-max+1 (= 1) would
|
||||
// collide with the stamped rows on the post-rename UPDATE, failing the
|
||||
// page and leaving the renamed fence disagreeing with the DB.
|
||||
for (let n = 1; n <= 3; n++) {
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
await (engine as any).db.query(
|
||||
`INSERT INTO facts (source_id, entity_slug, fact, kind, visibility, notability,
|
||||
valid_from, source, confidence, row_num, source_markdown_slug)
|
||||
VALUES ('default', 'people/alice', $1, 'fact', 'private', 'medium',
|
||||
now(), 'mcp:extract_facts', 1.0, $2, 'people/alice')`,
|
||||
[`stamped ${n}`, n],
|
||||
);
|
||||
}
|
||||
await seedLegacyFact('Deposited remotely');
|
||||
|
||||
const result = await phaseBFenceFacts(engine, { dryRun: false });
|
||||
expect(result.status).toBe('complete');
|
||||
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
const rows = await (engine as any).db.query(
|
||||
`SELECT row_num FROM facts WHERE fact = 'Deposited remotely'`,
|
||||
);
|
||||
expect(rows.rows[0].row_num).toBe(4);
|
||||
const body = readFileSync(join(brainDir, 'people/alice.md'), 'utf-8');
|
||||
expect(body).toContain('| 4 | Deposited remotely |');
|
||||
});
|
||||
});
|
||||
@@ -292,6 +292,49 @@ describe('lookupSourceLocalPath', () => {
|
||||
});
|
||||
});
|
||||
|
||||
describe('writeFactsToFence — fence/DB divergence (#2044)', () => {
|
||||
test('seeds row_num past the DB max when the fence lags the DB', async () => {
|
||||
// Simulate the divergence class from #2044: DB rows were stamped with
|
||||
// row_nums against a fence written at a path this code no longer reads
|
||||
// (e.g. the pre-"Local patch 2026-06-11" wrong-path writes). The page
|
||||
// on disk has NO fence, but the DB already holds row_num 1..3 for the
|
||||
// slug. Pre-fix, the next deposit re-assigned row_num=1 from fence
|
||||
// text alone and the whole insertFacts batch failed on
|
||||
// idx_facts_fence_key.
|
||||
for (let n = 1; n <= 3; n++) {
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
await (engine as any).db.query(
|
||||
`INSERT INTO facts (source_id, entity_slug, fact, kind, visibility, notability,
|
||||
valid_from, source, confidence, row_num, source_markdown_slug)
|
||||
VALUES ('default', 'people/dana', $1, 'fact', 'private', 'medium',
|
||||
now(), 'mcp:extract_facts', 1.0, $2, 'people/dana')`,
|
||||
[`old claim ${n}`, n],
|
||||
);
|
||||
}
|
||||
|
||||
const result = await writeFactsToFence(
|
||||
engine,
|
||||
{ sourceId: 'default', localPath: brainDir, slug: 'people/dana' },
|
||||
[baseInput({ fact: 'second deposit' })],
|
||||
);
|
||||
|
||||
expect(result.fenceWriteFailed).toBeUndefined();
|
||||
expect(result.inserted).toBe(1);
|
||||
|
||||
// The new row landed PAST the DB max, not at fence-max+1 (= 1).
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
const rows = await (engine as any).db.query(
|
||||
'SELECT row_num FROM facts WHERE id = $1',
|
||||
[result.ids[0]],
|
||||
);
|
||||
expect(rows.rows[0].row_num).toBe(4);
|
||||
|
||||
// And the on-disk fence carries the same row_num — fence and DB agree.
|
||||
const body = readFileSync(join(brainDir, 'people/dana.md'), 'utf-8');
|
||||
expect(body).toContain('| 4 | second deposit |');
|
||||
});
|
||||
});
|
||||
|
||||
// Cleanup any leftover tempdirs after the whole suite.
|
||||
afterAll(() => {
|
||||
// No-op: each test cleaned up via the beforeEach; this is a safety net.
|
||||
|
||||
@@ -5,7 +5,7 @@
|
||||
* - Batch insert N rows persists row_num + source_markdown_slug
|
||||
* - Empty batch is a no-op
|
||||
* - Returns ids in input-order
|
||||
* - v51 partial UNIQUE index rolls back the whole batch on a collision
|
||||
* - v51 partial UNIQUE collision skips only the colliding row (#2044)
|
||||
* - deleteFactsForPage scopes by (source_id, source_markdown_slug);
|
||||
* never touches other pages or pre-v51 NULL-source_markdown_slug rows
|
||||
* - deleteFactsForPage on an empty page returns deleted:0 (idempotent)
|
||||
@@ -135,30 +135,29 @@ describe('engine.insertFacts — batch insert', () => {
|
||||
});
|
||||
});
|
||||
|
||||
test('v51 partial UNIQUE index rolls back the whole batch on collision', async () => {
|
||||
test('v51 partial UNIQUE collision skips ONLY the colliding row (#2044)', async () => {
|
||||
// Seed row #1 first.
|
||||
await engine.insertFacts([fixtureFact(1, { fact: 'seeded' })], { source_id: 'default' });
|
||||
|
||||
// Now try to batch-insert rows that include a colliding row_num=1.
|
||||
let threw = false;
|
||||
try {
|
||||
await engine.insertFacts(
|
||||
[
|
||||
fixtureFact(2, { fact: 'second' }),
|
||||
fixtureFact(1, { fact: 'collides' }), // row_num=1 on same (source_id, source_markdown_slug)
|
||||
fixtureFact(3, { fact: 'third' }),
|
||||
],
|
||||
{ source_id: 'default' },
|
||||
);
|
||||
} catch {
|
||||
threw = true;
|
||||
}
|
||||
expect(threw).toBe(true);
|
||||
// Batch-insert rows that include a colliding row_num=1. Pre-#2044 this
|
||||
// threw and rolled back the whole batch, making a second remote
|
||||
// extract_facts deposit to an already-fenced page a hard failure. Now
|
||||
// ON CONFLICT DO NOTHING skips the colliding row and keeps the rest.
|
||||
const result = await engine.insertFacts(
|
||||
[
|
||||
fixtureFact(2, { fact: 'second' }),
|
||||
fixtureFact(1, { fact: 'collides' }), // row_num=1 on same (source_id, source_markdown_slug)
|
||||
fixtureFact(3, { fact: 'third' }),
|
||||
],
|
||||
{ source_id: 'default' },
|
||||
);
|
||||
expect(result.inserted).toBe(2);
|
||||
expect(result.ids).toHaveLength(2);
|
||||
|
||||
// Verify the transaction rolled back — only the seeded row should remain.
|
||||
// The seeded row survives untouched; the colliding claim is skipped.
|
||||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||||
const rows = await (engine as any).db.query('SELECT fact FROM facts ORDER BY id');
|
||||
expect(rows.rows.map((r: { fact: string }) => r.fact)).toEqual(['seeded']);
|
||||
expect(rows.rows.map((r: { fact: string }) => r.fact)).toEqual(['seeded', 'second', 'third']);
|
||||
});
|
||||
|
||||
test('different source_markdown_slug values DO NOT collide on the same row_num', async () => {
|
||||
|
||||
@@ -9,7 +9,6 @@ import {
|
||||
parseTimelineEntries,
|
||||
isAutoLinkEnabled,
|
||||
FRONTMATTER_LINK_MAP,
|
||||
unwrapWikilink,
|
||||
type SlugResolver,
|
||||
} from '../src/core/link-extraction.ts';
|
||||
import type { BrainEngine } from '../src/core/engine.ts';
|
||||
@@ -1292,175 +1291,3 @@ describe('parseTimelineEntries — Format 3: inline [Source: ..., YYYY-MM-DD] ci
|
||||
expect(parseTimelineEntries('[Source: import batch, 2025-07-01]')).toHaveLength(0);
|
||||
});
|
||||
});
|
||||
// ─── Frontmatter [[wikilink]] + slug-path resolution ──────────────────────
|
||||
// Mainstream Obsidian authors frontmatter links as `related: ["[[Page]]"]`,
|
||||
// and PARA-numbered vaults use digit-leading / nested slug paths like
|
||||
// `[[90-people/nicolai]]`. Both were silently dropped: brackets were treated
|
||||
// as part of the value and the step-1 slug regex (`^[a-z]…`) rejected
|
||||
// digit-leading / nested paths, while full-path fuzzy scored below threshold.
|
||||
// Fix: unwrapWikilink() before resolution + an exact getPage() for any
|
||||
// slug-shaped value (exact-match only → no false positives).
|
||||
|
||||
describe('unwrapWikilink', () => {
|
||||
test('wrapped title → bare title', () => {
|
||||
expect(unwrapWikilink('[[Monday Range]]')).toBe('Monday Range');
|
||||
});
|
||||
test('wrapped slug-path (digit-leading folder) → bare slug', () => {
|
||||
expect(unwrapWikilink('[[90-people/nicolai]]')).toBe('90-people/nicolai');
|
||||
});
|
||||
test('wrapped nested slug-path → bare slug', () => {
|
||||
expect(unwrapWikilink('[[01-trading/wiki/strategies/opening-range-breakout]]'))
|
||||
.toBe('01-trading/wiki/strategies/opening-range-breakout');
|
||||
});
|
||||
test('strips |alias', () => {
|
||||
expect(unwrapWikilink('[[90-people/nicolai|Nicolai]]')).toBe('90-people/nicolai');
|
||||
});
|
||||
test('strips #heading', () => {
|
||||
expect(unwrapWikilink('[[Page#Section]]')).toBe('Page');
|
||||
});
|
||||
test('strips ^block', () => {
|
||||
expect(unwrapWikilink('[[Page^abc123]]')).toBe('Page');
|
||||
});
|
||||
test('surrounding whitespace tolerated', () => {
|
||||
expect(unwrapWikilink(' [[Page]] ')).toBe('Page');
|
||||
});
|
||||
test('bare title passes through unchanged', () => {
|
||||
expect(unwrapWikilink('Monday Range')).toBe('Monday Range');
|
||||
});
|
||||
test('bare slug passes through unchanged', () => {
|
||||
expect(unwrapWikilink('90-people/nicolai')).toBe('90-people/nicolai');
|
||||
});
|
||||
test('partially-wrapped value is NOT unwrapped (anchored)', () => {
|
||||
// Not a wholly-wrapped value → left intact so existing behavior is exact.
|
||||
expect(unwrapWikilink('see [[Page]] for detail')).toBe('see [[Page]] for detail');
|
||||
});
|
||||
});
|
||||
|
||||
describe('makeResolver — slug-path exact getPage (step 1 broadened)', () => {
|
||||
function fakeEngine(
|
||||
slugs: string[],
|
||||
fuzzyMap: Map<string, { slug: string; similarity: number }> = new Map(),
|
||||
): BrainEngine {
|
||||
const lookup = new Set(slugs);
|
||||
return {
|
||||
async getPage(slug: string) { return lookup.has(slug) ? { slug } as any : null; },
|
||||
async findByTitleFuzzy(name: string) { return fuzzyMap.get(name) ?? null; },
|
||||
async searchKeyword() { return []; },
|
||||
} as unknown as BrainEngine;
|
||||
}
|
||||
|
||||
test('digit-leading folder slug resolves via exact getPage', async () => {
|
||||
const r = makeResolver(fakeEngine(['90-people/nicolai']));
|
||||
expect(await r.resolve('90-people/nicolai')).toBe('90-people/nicolai');
|
||||
});
|
||||
|
||||
test('nested (>2 segment) slug resolves via exact getPage', async () => {
|
||||
const r = makeResolver(fakeEngine(['01-trading/wiki/strategies/opening-range-breakout']));
|
||||
expect(await r.resolve('01-trading/wiki/strategies/opening-range-breakout'))
|
||||
.toBe('01-trading/wiki/strategies/opening-range-breakout');
|
||||
});
|
||||
|
||||
test('regression: single-segment lowercase slug still resolves', async () => {
|
||||
const r = makeResolver(fakeEngine(['people/pedro']));
|
||||
expect(await r.resolve('people/pedro')).toBe('people/pedro');
|
||||
});
|
||||
|
||||
test('exact-only: slug-shaped value with no matching page falls through (no false positive)', async () => {
|
||||
// `90-people/ghost` is slug-shaped but absent → step-1 getPage misses,
|
||||
// no fuzzy hit → null. Never invents an edge.
|
||||
const r = makeResolver(fakeEngine(['90-people/nicolai']));
|
||||
expect(await r.resolve('90-people/ghost')).toBeNull();
|
||||
});
|
||||
|
||||
test('non-slug value still routes to fuzzy', async () => {
|
||||
const r = makeResolver(fakeEngine(
|
||||
['01-trading/monday-range'],
|
||||
new Map([['Monday Range', { slug: '01-trading/monday-range', similarity: 1 }]]),
|
||||
));
|
||||
expect(await r.resolve('Monday Range')).toBe('01-trading/monday-range');
|
||||
});
|
||||
});
|
||||
|
||||
describe('extractFrontmatterLinks — [[wikilink]] related: values (end-to-end)', () => {
|
||||
function fakeEngine(
|
||||
slugs: string[],
|
||||
fuzzyMap: Map<string, { slug: string; similarity: number }> = new Map(),
|
||||
): BrainEngine {
|
||||
const lookup = new Set(slugs);
|
||||
return {
|
||||
async getPage(slug: string) { return lookup.has(slug) ? { slug } as any : null; },
|
||||
async findByTitleFuzzy(name: string) { return fuzzyMap.get(name) ?? null; },
|
||||
async searchKeyword() { return []; },
|
||||
} as unknown as BrainEngine;
|
||||
}
|
||||
|
||||
test('wrapped slug-path related: resolves (the core win)', async () => {
|
||||
const resolver = makeResolver(fakeEngine(['90-people/nicolai']));
|
||||
const { candidates, unresolved } = await extractFrontmatterLinks(
|
||||
'wiki/originals/ideas/note', 'note' as never,
|
||||
{ related: '[[90-people/nicolai]]' }, resolver,
|
||||
);
|
||||
expect(unresolved).toHaveLength(0);
|
||||
expect(candidates).toHaveLength(1);
|
||||
expect(candidates[0]).toMatchObject({
|
||||
fromSlug: 'wiki/originals/ideas/note',
|
||||
targetSlug: '90-people/nicolai',
|
||||
linkType: 'related_to',
|
||||
linkSource: 'frontmatter',
|
||||
});
|
||||
});
|
||||
|
||||
test('wrapped nested slug-path related: resolves', async () => {
|
||||
const resolver = makeResolver(fakeEngine(['01-trading/wiki/strategies/opening-range-breakout']));
|
||||
const { candidates } = await extractFrontmatterLinks(
|
||||
'wiki/note', 'note' as never,
|
||||
{ related: ['[[01-trading/wiki/strategies/opening-range-breakout]]'] }, resolver,
|
||||
);
|
||||
expect(candidates).toHaveLength(1);
|
||||
expect(candidates[0].targetSlug).toBe('01-trading/wiki/strategies/opening-range-breakout');
|
||||
});
|
||||
|
||||
test('wrapped value with |alias resolves to the target', async () => {
|
||||
const resolver = makeResolver(fakeEngine(['90-people/nicolai']));
|
||||
const { candidates } = await extractFrontmatterLinks(
|
||||
'wiki/note', 'note' as never,
|
||||
{ related: '[[90-people/nicolai|Nicolai]]' }, resolver,
|
||||
);
|
||||
expect(candidates).toHaveLength(1);
|
||||
expect(candidates[0].targetSlug).toBe('90-people/nicolai');
|
||||
});
|
||||
|
||||
test('regression: bare slug related: still resolves', async () => {
|
||||
const resolver = makeResolver(fakeEngine(['90-people/nicolai']));
|
||||
const { candidates } = await extractFrontmatterLinks(
|
||||
'wiki/note', 'note' as never,
|
||||
{ related: '90-people/nicolai' }, resolver,
|
||||
);
|
||||
expect(candidates).toHaveLength(1);
|
||||
expect(candidates[0].targetSlug).toBe('90-people/nicolai');
|
||||
});
|
||||
|
||||
test('regression: wrapped title resolves via fuzzy (brackets harmless)', async () => {
|
||||
const resolver = makeResolver(fakeEngine(
|
||||
['01-trading/monday-range'],
|
||||
new Map([['Monday Range', { slug: '01-trading/monday-range', similarity: 1 }]]),
|
||||
));
|
||||
const { candidates } = await extractFrontmatterLinks(
|
||||
'wiki/note', 'note' as never,
|
||||
{ related: '[[Monday Range]]' }, resolver,
|
||||
);
|
||||
expect(candidates).toHaveLength(1);
|
||||
expect(candidates[0].targetSlug).toBe('01-trading/monday-range');
|
||||
});
|
||||
|
||||
test('unknown wrapped slug → unresolved (no crash), original value preserved', async () => {
|
||||
const resolver = makeResolver(fakeEngine(['90-people/nicolai']));
|
||||
const { candidates, unresolved } = await extractFrontmatterLinks(
|
||||
'wiki/note', 'note' as never,
|
||||
{ related: '[[99-archive/does-not-exist]]' }, resolver,
|
||||
);
|
||||
expect(candidates).toHaveLength(0);
|
||||
expect(unresolved).toHaveLength(1);
|
||||
expect(unresolved[0]).toEqual({ field: 'related', name: '[[99-archive/does-not-exist]]' });
|
||||
});
|
||||
});
|
||||
|
||||
Reference in New Issue
Block a user