mirror of
https://github.com/garrytan/gbrain.git
synced 2026-08-17 18:32:41 +00:00
Compare commits
2
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
9e044021ef | ||
|
|
553515c82c |
+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})`);
|
||||
|
||||
@@ -2059,6 +2059,8 @@ export async function registerBuiltinHandlers(
|
||||
sourceId,
|
||||
windowSeconds,
|
||||
brainDir: repoPath,
|
||||
// #2750: worker cancel/timeout/lock-loss propagates into the drain.
|
||||
abortSignal: job.signal,
|
||||
});
|
||||
} catch (e) {
|
||||
if (e instanceof LockUnavailableError) {
|
||||
|
||||
@@ -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;
|
||||
|
||||
@@ -23,6 +23,10 @@
|
||||
*/
|
||||
|
||||
import type { BrainEngine } from '../engine.ts';
|
||||
import { anySignal } from '../abort-check.ts';
|
||||
|
||||
/** Fresh cleanup budget for the lock release after the window signal fires. */
|
||||
const LOCK_RELEASE_GRACE_MS = 5_000;
|
||||
|
||||
export interface ExtractAtomsDrainDeps {
|
||||
/**
|
||||
@@ -30,13 +34,13 @@ export interface ExtractAtomsDrainDeps {
|
||||
* via `withRefreshingLock`. MUST throw when the lock is held by another
|
||||
* process (e.g. `LockUnavailableError`) — the drain lets that propagate so
|
||||
* the caller can report `cycle_already_running` and exit, matching the
|
||||
* routine cycle's skip contract.
|
||||
* routine cycle's skip contract. The signal bounds lock acquisition too.
|
||||
*/
|
||||
withLock: <T>(work: () => Promise<T>) => Promise<T>;
|
||||
/** Process one bounded batch (rediscovers eligibility). Returns counts. */
|
||||
runBatch: () => Promise<{ extracted: number; skipped: number }>;
|
||||
withLock: <T>(work: () => Promise<T>, signal: AbortSignal) => Promise<T>;
|
||||
/** Process one batch. The signal fires at the drain wallclock deadline. */
|
||||
runBatch: (signal: AbortSignal) => Promise<{ extracted: number; skipped: number }>;
|
||||
/** Count remaining eligible-but-unextracted pages, or null on query error. */
|
||||
countRemaining: () => Promise<number | null>;
|
||||
countRemaining: (signal: AbortSignal) => Promise<number | null>;
|
||||
/** Injectable clock. Production: Date.now. */
|
||||
now: () => number;
|
||||
/** Optional progress sink (one line per batch). */
|
||||
@@ -48,6 +52,8 @@ export interface ExtractAtomsDrainOpts {
|
||||
windowMs: number;
|
||||
/** Hard cap on batches (belt-and-suspenders against a 0-progress loop). Default 1000. */
|
||||
maxBatches?: number;
|
||||
/** External caller cancellation (worker timeout / shutdown). */
|
||||
abortSignal?: AbortSignal;
|
||||
}
|
||||
|
||||
export interface ExtractAtomsDrainResult {
|
||||
@@ -68,35 +74,79 @@ export async function runExtractAtomsDrain(
|
||||
opts: ExtractAtomsDrainOpts,
|
||||
): Promise<ExtractAtomsDrainResult> {
|
||||
const maxBatches = opts.maxBatches ?? 1000;
|
||||
return deps.withLock(async () => {
|
||||
const deadline = deps.now() + opts.windowMs;
|
||||
const deadline = deps.now() + opts.windowMs;
|
||||
// #2750: the window used to be checked only BETWEEN batches, so one slow
|
||||
// batch (sequential LLM calls) or a hung lock/count/write overran it without
|
||||
// bound (observed window=120s → 282.5s). A real-time deadline signal now
|
||||
// cancels (Postgres) or abandons (PGLite, cooperative) whatever is in
|
||||
// flight; the injected clock still drives loop-boundary checks so the pure
|
||||
// loop stays unit-testable.
|
||||
const signal = anySignal(
|
||||
AbortSignal.timeout(Math.max(1, opts.windowMs)),
|
||||
opts.abortSignal,
|
||||
);
|
||||
const result: ExtractAtomsDrainResult = await deps.withLock(async () => {
|
||||
let extracted = 0;
|
||||
let skipped = 0;
|
||||
let batches = 0;
|
||||
let stopped: ExtractAtomsDrainResult['stopped'] = 'window';
|
||||
|
||||
while (deps.now() < deadline) {
|
||||
while (deps.now() < deadline && !signal.aborted) {
|
||||
if (batches >= maxBatches) { stopped = 'max_batches'; break; }
|
||||
|
||||
const before = await deps.countRemaining();
|
||||
let before: number | null;
|
||||
try {
|
||||
before = await deps.countRemaining(signal);
|
||||
} catch (err) {
|
||||
if (signal.aborted) break;
|
||||
throw err;
|
||||
}
|
||||
if (before === 0) { stopped = 'drained'; break; }
|
||||
|
||||
const r = await deps.runBatch();
|
||||
// The backlog count consumed the same wallclock budget — re-check so a
|
||||
// slow count can't hand the batch a window that already expired.
|
||||
if (deps.now() >= deadline || signal.aborted) break;
|
||||
|
||||
let r: { extracted: number; skipped: number };
|
||||
try {
|
||||
r = await deps.runBatch(signal);
|
||||
} catch (err) {
|
||||
if (signal.aborted) break;
|
||||
throw err;
|
||||
}
|
||||
extracted += r.extracted;
|
||||
skipped += r.skipped;
|
||||
batches++;
|
||||
deps.onBatch?.({ batch: batches, extracted: r.extracted, remaining: before });
|
||||
|
||||
// A deadline abort inside the batch can surface as zero progress;
|
||||
// window exhaustion wins over the generic no_progress label.
|
||||
if (deps.now() >= deadline || signal.aborted) break;
|
||||
|
||||
// Stop if a batch made zero forward progress — extraction is failing or
|
||||
// everything left is ineligible (e.g. all skipped). Prevents a hot loop
|
||||
// that spends budget without draining.
|
||||
if (r.extracted === 0 && r.skipped === 0) { stopped = 'no_progress'; break; }
|
||||
}
|
||||
|
||||
const remaining = await deps.countRemaining();
|
||||
// After the window elapsed, don't spend more unbounded time on a final
|
||||
// count — report remaining as unknown instead of overrunning further.
|
||||
const windowElapsed = signal.aborted || deps.now() >= deadline;
|
||||
let remaining: number | null = null;
|
||||
if (!windowElapsed) {
|
||||
try {
|
||||
remaining = await deps.countRemaining(signal);
|
||||
} catch (err) {
|
||||
if (!signal.aborted) throw err;
|
||||
}
|
||||
}
|
||||
if (remaining === 0) stopped = 'drained';
|
||||
return { phase: 'extract_atoms', status: 'ok', extracted, skipped, remaining, batches, stopped };
|
||||
});
|
||||
}, signal);
|
||||
// Internal window expiry is a normal partial result. An EXTERNAL abort
|
||||
// (worker cancel/timeout/shutdown) must reject so Minion records the abort.
|
||||
if (opts.abortSignal?.aborted) throw opts.abortSignal.reason;
|
||||
return result;
|
||||
}
|
||||
|
||||
// ─── Shared wiring helper (v0.42.x #1685 DECISION 5A) ──────────────────────
|
||||
@@ -134,6 +184,8 @@ export interface DrainForSourceOpts {
|
||||
maxBatches?: number;
|
||||
/** Optional per-batch progress sink (stderr line in dream; job progress in the handler). */
|
||||
onBatch?: ExtractAtomsDrainDeps['onBatch'];
|
||||
/** Worker cancellation / shutdown signal (Minion `job.signal`). */
|
||||
abortSignal?: AbortSignal;
|
||||
}
|
||||
|
||||
export async function runExtractAtomsDrainForSource(
|
||||
@@ -149,12 +201,17 @@ export async function runExtractAtomsDrainForSource(
|
||||
|
||||
return runExtractAtomsDrain(
|
||||
{
|
||||
withLock: (work) => withRefreshingLock(engine, lockId, work, { ttlMinutes: 5 }),
|
||||
runBatch: async () => {
|
||||
withLock: (work, signal) => withRefreshingLock(engine, lockId, work, {
|
||||
ttlMinutes: 5,
|
||||
signal,
|
||||
releaseTimeoutMs: LOCK_RELEASE_GRACE_MS,
|
||||
}),
|
||||
runBatch: async (signal) => {
|
||||
const r = await runPhaseExtractAtoms(engine, {
|
||||
sourceId: extractionSourceId,
|
||||
dryRun: false,
|
||||
brainDir: opts.brainDir,
|
||||
abortSignal: signal,
|
||||
});
|
||||
const d = (r.details ?? {}) as Record<string, unknown>;
|
||||
return {
|
||||
@@ -162,10 +219,14 @@ export async function runExtractAtomsDrainForSource(
|
||||
skipped: Number(d.duplicates_skipped ?? 0),
|
||||
};
|
||||
},
|
||||
countRemaining: () => countExtractAtomsBacklog(engine, extractionSourceId),
|
||||
countRemaining: (signal) => countExtractAtomsBacklog(engine, extractionSourceId, signal),
|
||||
now: Date.now,
|
||||
onBatch: opts.onBatch,
|
||||
},
|
||||
{ windowMs: opts.windowSeconds * 1000, maxBatches: opts.maxBatches },
|
||||
{
|
||||
windowMs: opts.windowSeconds * 1000,
|
||||
maxBatches: opts.maxBatches,
|
||||
abortSignal: opts.abortSignal,
|
||||
},
|
||||
);
|
||||
}
|
||||
|
||||
@@ -58,6 +58,10 @@ import { createHash } from 'crypto';
|
||||
import { slugifySegment } from '../sync.ts';
|
||||
|
||||
const DEFAULT_BUDGET_USD = 0.3;
|
||||
// #2750: fresh wallclock budget for the receipt/rollup bookkeeping writes when
|
||||
// the caller's deadline already fired — committed atoms must not lose their
|
||||
// cost/receipt trail, but the writes can't be unbounded either.
|
||||
const BOOKKEEPING_GRACE_MS = 5_000;
|
||||
|
||||
// v0.42+ TODO: read atom_type enum from active pack manifest at runtime.
|
||||
const ATOM_TYPES = [
|
||||
@@ -155,6 +159,13 @@ export interface ExtractAtomsOpts {
|
||||
* `heartbeat()` on the passed reporter.
|
||||
*/
|
||||
progress?: ProgressReporter;
|
||||
/**
|
||||
* #2750: caller deadline/cancellation. Forwarded to every gateway call and
|
||||
* DB query/write so the drain window bounds real lifetime, plus a
|
||||
* cooperative between-item check (the PGLite path, where query abort only
|
||||
* abandons the waiter).
|
||||
*/
|
||||
abortSignal?: AbortSignal;
|
||||
}
|
||||
|
||||
interface ExtractedAtom {
|
||||
@@ -212,6 +223,7 @@ export async function discoverExtractablePages(
|
||||
engine: BrainEngine,
|
||||
sourceId: string,
|
||||
affectedSlugs?: string[],
|
||||
abortSignal?: AbortSignal,
|
||||
): Promise<DiscoveredPage[]> {
|
||||
const hasFilter = Array.isArray(affectedSlugs) && affectedSlugs.length > 0;
|
||||
const sql = `
|
||||
@@ -251,13 +263,16 @@ export async function discoverExtractablePages(
|
||||
slug: string;
|
||||
compiled_truth: string;
|
||||
content_hash: string;
|
||||
}>(sql, params);
|
||||
}>(sql, params, { signal: abortSignal });
|
||||
return rows.map((r) => ({
|
||||
slug: r.slug,
|
||||
content: r.compiled_truth,
|
||||
contentHash: r.content_hash,
|
||||
}));
|
||||
} catch (err) {
|
||||
// A deadline abort is not a fail-soft condition — propagate so the
|
||||
// caller stops instead of proceeding with an empty page list.
|
||||
if (abortSignal?.aborted) throw err;
|
||||
const msg = err instanceof Error ? err.message : String(err);
|
||||
console.error(`[extract_atoms] page-discovery query failed: ${msg}`);
|
||||
return []; // fail-soft: transcript path still proceeds
|
||||
@@ -282,6 +297,7 @@ export async function discoverExtractablePages(
|
||||
export async function countExtractAtomsBacklog(
|
||||
engine: BrainEngine,
|
||||
sourceId?: string,
|
||||
abortSignal?: AbortSignal,
|
||||
): Promise<number | null> {
|
||||
try {
|
||||
// Two modes: scoped (the phase's per-source `remaining`) vs brain-wide
|
||||
@@ -321,9 +337,10 @@ export async function countExtractAtomsBacklog(
|
||||
const params = scoped
|
||||
? [sourceId, extractableTypes, MIN_PAGE_CHARS_FOR_EXTRACTION]
|
||||
: [extractableTypes, MIN_PAGE_CHARS_FOR_EXTRACTION];
|
||||
const rows = await engine.executeRaw<{ cnt: string | number }>(sql, params);
|
||||
const rows = await engine.executeRaw<{ cnt: string | number }>(sql, params, { signal: abortSignal });
|
||||
return Number(rows[0]?.cnt ?? 0);
|
||||
} catch (err) {
|
||||
if (abortSignal?.aborted) throw err;
|
||||
const msg = err instanceof Error ? err.message : String(err);
|
||||
console.error(`[extract_atoms] backlog count failed: ${msg}`);
|
||||
return null;
|
||||
@@ -350,6 +367,7 @@ export async function atomsExistingForHashes(
|
||||
engine: BrainEngine,
|
||||
sourceId: string,
|
||||
contentHash16s: string[],
|
||||
abortSignal?: AbortSignal,
|
||||
): Promise<Set<string>> {
|
||||
if (contentHash16s.length === 0) return new Set();
|
||||
try {
|
||||
@@ -361,9 +379,11 @@ export async function atomsExistingForHashes(
|
||||
AND deleted_at IS NULL
|
||||
AND frontmatter->>'source_hash' = ANY($2::text[])`,
|
||||
[sourceId, contentHash16s],
|
||||
{ signal: abortSignal },
|
||||
);
|
||||
return new Set(rows.map(r => r.h));
|
||||
} catch (err) {
|
||||
if (abortSignal?.aborted) throw err;
|
||||
const msg = err instanceof Error ? err.message : String(err);
|
||||
console.error(`[extract_atoms] batch idempotency check failed (assuming none extracted): ${msg}`);
|
||||
return new Set();
|
||||
@@ -384,6 +404,7 @@ export async function runPhaseExtractAtoms(
|
||||
): Promise<PhaseResult> {
|
||||
const sourceId = opts.sourceId ?? 'default';
|
||||
const chat = opts._chat ?? gatewayChat;
|
||||
if (opts.abortSignal?.aborted) throw opts.abortSignal.reason;
|
||||
|
||||
// 1a. Get transcripts (test seam OR production discovery).
|
||||
// v0.41.2.1: config loader switched to loadConfigWithEngine() so the
|
||||
@@ -425,7 +446,7 @@ export async function runPhaseExtractAtoms(
|
||||
if (opts._pages !== undefined) {
|
||||
pages = opts._pages;
|
||||
} else {
|
||||
pages = await discoverExtractablePages(engine, sourceId, opts.affectedSlugs);
|
||||
pages = await discoverExtractablePages(engine, sourceId, opts.affectedSlugs, opts.abortSignal);
|
||||
}
|
||||
|
||||
// 2. Apply transcript-side source-hash idempotency in ONE batch query
|
||||
@@ -437,7 +458,7 @@ export async function runPhaseExtractAtoms(
|
||||
// Surface a heartbeat before the batch query so even an instant
|
||||
// short-circuit shows a sign of life (closes Issue 2 silent-phase pain).
|
||||
opts.progress?.heartbeat(`checking existing atoms for ${allHashes16.length} transcripts`);
|
||||
const existingHashes = await atomsExistingForHashes(engine, sourceId, allHashes16);
|
||||
const existingHashes = await atomsExistingForHashes(engine, sourceId, allHashes16, opts.abortSignal);
|
||||
for (const t of transcripts) {
|
||||
if (existingHashes.has(t.contentHash.slice(0, 16))) {
|
||||
duplicatesSkipped++;
|
||||
@@ -501,6 +522,7 @@ export async function runPhaseExtractAtoms(
|
||||
const failures: Array<{ source: string; error: string }> = [];
|
||||
let estimatedSpendUsd = 0;
|
||||
const budgetCap = DEFAULT_BUDGET_USD;
|
||||
let deadlineAborted = false;
|
||||
|
||||
// v0.41.19.0 (T3): throttled yield helper. Fires `opts.yieldDuringPhase`
|
||||
// every 30s. Cycle.ts threads `buildYieldDuringPhase(lock, outer)` so
|
||||
@@ -526,6 +548,12 @@ export async function runPhaseExtractAtoms(
|
||||
}
|
||||
|
||||
for (const item of work) {
|
||||
// #2750: cooperative between-item abort. Works on every engine — this is
|
||||
// the primary bound on PGLite, where query abort only abandons the waiter.
|
||||
if (opts.abortSignal?.aborted) {
|
||||
deadlineAborted = true;
|
||||
break;
|
||||
}
|
||||
await maybeYield();
|
||||
if (estimatedSpendUsd >= budgetCap) {
|
||||
if (item.kind === 'transcript') transcriptsSkipped++;
|
||||
@@ -544,16 +572,22 @@ export async function runPhaseExtractAtoms(
|
||||
},
|
||||
],
|
||||
maxTokens: 2000,
|
||||
abortSignal: opts.abortSignal,
|
||||
});
|
||||
// Rough cost estimate — Haiku at ~$0.80/M input + $4/M output.
|
||||
// A completed gateway call is billable even if the deadline fires
|
||||
// immediately afterward, so record usage BEFORE the abort check.
|
||||
estimatedSpendUsd +=
|
||||
(result.usage.input_tokens * 0.8 + result.usage.output_tokens * 4.0) / 1_000_000;
|
||||
if (opts.abortSignal?.aborted) {
|
||||
deadlineAborted = true;
|
||||
break;
|
||||
}
|
||||
// Post-await yield: closes the "long LLM call past TTL" hazard
|
||||
// codex flagged. The 30s throttle inside maybeYield bounds the
|
||||
// actual refresh rate so this is cheap when calls are fast.
|
||||
await maybeYield();
|
||||
|
||||
// Rough cost estimate — Haiku at ~$0.80/M input + $4/M output
|
||||
estimatedSpendUsd +=
|
||||
(result.usage.input_tokens * 0.8 + result.usage.output_tokens * 4.0) / 1_000_000;
|
||||
|
||||
const atoms = parseAtomsResponse(result.text);
|
||||
if (atoms.length === 0) {
|
||||
if (item.kind === 'transcript') transcriptsProcessed++;
|
||||
@@ -592,7 +626,7 @@ export async function runPhaseExtractAtoms(
|
||||
},
|
||||
timeline: '',
|
||||
},
|
||||
{ sourceId },
|
||||
{ sourceId, signal: opts.abortSignal },
|
||||
);
|
||||
totalAtomsExtracted++;
|
||||
}
|
||||
@@ -605,6 +639,11 @@ export async function runPhaseExtractAtoms(
|
||||
// Reporter rate-limits to ~1 line/sec; safe to tick every iter.
|
||||
opts.progress?.tick(1, `${totalAtomsExtracted} atoms / ${duplicatesSkipped} skipped`);
|
||||
} catch (err) {
|
||||
// A deadline abort is a partial result, not a per-item failure.
|
||||
if (opts.abortSignal?.aborted) {
|
||||
deadlineAborted = true;
|
||||
break;
|
||||
}
|
||||
failures.push({
|
||||
source: originLabel,
|
||||
error: err instanceof Error ? err.message : String(err),
|
||||
@@ -615,6 +654,12 @@ export async function runPhaseExtractAtoms(
|
||||
// v0.42 Wave B2: write extract receipt + rollup row when the phase
|
||||
// actually extracted atoms. Both are best-effort per F-OUT-19 —
|
||||
// audit-trail / search-visibility surfaces don't block the phase result.
|
||||
//
|
||||
// #2750: bookkeeping runs on a FRESH short grace signal, never the caller's
|
||||
// work deadline — the deadline may have already fired (partial run) and
|
||||
// committed atoms must not lose their receipt/cost trail; but the writes
|
||||
// stay bounded so the overrun is capped at the grace window.
|
||||
const bookkeepingSignal = opts.dryRun ? undefined : AbortSignal.timeout(BOOKKEEPING_GRACE_MS);
|
||||
if (!opts.dryRun && totalAtomsExtracted > 0) {
|
||||
const runId = `atoms-${Date.now().toString(36)}-${sourceId.slice(0, 4)}`;
|
||||
try {
|
||||
@@ -629,19 +674,24 @@ export async function runPhaseExtractAtoms(
|
||||
summary:
|
||||
`Extracted ${totalAtomsExtracted} atoms from ` +
|
||||
`${transcriptsProcessed} transcripts + ${pagesProcessed} pages.`,
|
||||
});
|
||||
}, { signal: bookkeepingSignal });
|
||||
} catch (err) {
|
||||
console.error(`[extract_atoms] receipt write failed: ${(err as Error).message}`);
|
||||
}
|
||||
}
|
||||
if (!opts.dryRun) {
|
||||
await upsertExtractRollup(engine, {
|
||||
kind: 'atoms',
|
||||
source_id: sourceId,
|
||||
cost_delta: estimatedSpendUsd,
|
||||
round_completed_delta: failures.length === 0 ? 1 : 0,
|
||||
halt_delta: failures.length > 0 ? 1 : 0,
|
||||
});
|
||||
try {
|
||||
await upsertExtractRollup(engine, {
|
||||
kind: 'atoms',
|
||||
source_id: sourceId,
|
||||
cost_delta: estimatedSpendUsd,
|
||||
// A deadline-truncated run is not a completed round.
|
||||
round_completed_delta: failures.length === 0 && !deadlineAborted ? 1 : 0,
|
||||
halt_delta: failures.length > 0 ? 1 : 0,
|
||||
}, { signal: bookkeepingSignal });
|
||||
} catch (err) {
|
||||
console.error(`[extract_atoms] rollup write failed: ${(err as Error).message}`);
|
||||
}
|
||||
}
|
||||
|
||||
return {
|
||||
@@ -670,6 +720,7 @@ export async function runPhaseExtractAtoms(
|
||||
budget_usd: budgetCap,
|
||||
source_id: sourceId,
|
||||
dry_run: opts.dryRun ?? false,
|
||||
deadline_aborted: deadlineAborted,
|
||||
},
|
||||
};
|
||||
}
|
||||
|
||||
+50
-22
@@ -26,7 +26,8 @@ import type { BrainEngine } from './engine.ts';
|
||||
|
||||
export interface DbLockHandle {
|
||||
id: string;
|
||||
release: () => Promise<void>;
|
||||
/** Optional signal bounds the release DELETE (deadline-bound callers). */
|
||||
release: (signal?: AbortSignal) => Promise<void>;
|
||||
refresh: () => Promise<void>;
|
||||
}
|
||||
|
||||
@@ -173,6 +174,7 @@ export async function tryAcquireDbLock(
|
||||
engine: BrainEngine,
|
||||
lockId: string,
|
||||
ttlMinutes: number = DEFAULT_TTL_MINUTES,
|
||||
opts: { signal?: AbortSignal } = {},
|
||||
): Promise<DbLockHandle | null> {
|
||||
const pid = process.pid;
|
||||
const host = hostname();
|
||||
@@ -205,20 +207,26 @@ export async function tryAcquireDbLock(
|
||||
// `gbrain sync --break-lock --max-age <s>` uses last_refreshed_at (not
|
||||
// acquired_at) to identify wedged-but-alive holders without stealing
|
||||
// healthy long-running holders that are actively refreshing.
|
||||
const rows: Array<{ id: string }> = await sql`
|
||||
INSERT INTO gbrain_cycle_locks (id, holder_pid, holder_host, acquired_at, ttl_expires_at, last_refreshed_at)
|
||||
VALUES (${lockId}, ${pid}, ${host}, NOW(), NOW() + ${ttl}::interval, NOW())
|
||||
ON CONFLICT (id) DO UPDATE
|
||||
SET holder_pid = ${pid},
|
||||
holder_host = ${host},
|
||||
acquired_at = NOW(),
|
||||
ttl_expires_at = NOW() + ${ttl}::interval,
|
||||
last_refreshed_at = NOW()
|
||||
WHERE gbrain_cycle_locks.ttl_expires_at < NOW()
|
||||
AND (gbrain_cycle_locks.last_refreshed_at IS NULL
|
||||
OR gbrain_cycle_locks.last_refreshed_at < NOW() - ${stealGraceSeconds} * INTERVAL '1 second')
|
||||
RETURNING id
|
||||
`;
|
||||
// #2750: routed through executeRaw so a deadline-bound caller's signal
|
||||
// can cancel a hung acquire (pool exhaustion). Cancellation is
|
||||
// transactional; in the rare ambiguous-commit case the row's TTL is the
|
||||
// backstop (drain locks use a short 5-minute TTL).
|
||||
const rows = await engine.executeRaw<{ id: string }>(
|
||||
`INSERT INTO gbrain_cycle_locks (id, holder_pid, holder_host, acquired_at, ttl_expires_at, last_refreshed_at)
|
||||
VALUES ($1, $2, $3, NOW(), NOW() + $4::interval, NOW())
|
||||
ON CONFLICT (id) DO UPDATE
|
||||
SET holder_pid = $2,
|
||||
holder_host = $3,
|
||||
acquired_at = NOW(),
|
||||
ttl_expires_at = NOW() + $4::interval,
|
||||
last_refreshed_at = NOW()
|
||||
WHERE gbrain_cycle_locks.ttl_expires_at < NOW()
|
||||
AND (gbrain_cycle_locks.last_refreshed_at IS NULL
|
||||
OR gbrain_cycle_locks.last_refreshed_at < NOW() - $5 * INTERVAL '1 second')
|
||||
RETURNING id`,
|
||||
[lockId, pid, host, ttl, stealGraceSeconds],
|
||||
{ signal: opts.signal },
|
||||
);
|
||||
if (rows.length === 0) return null;
|
||||
const deregister = registerCleanup(`db-lock:${lockId}`, async () => {
|
||||
await sql`
|
||||
@@ -241,12 +249,17 @@ export async function tryAcquireDbLock(
|
||||
[ttl, lockId, pid],
|
||||
);
|
||||
},
|
||||
release: async () => {
|
||||
release: async (signal?: AbortSignal) => {
|
||||
deregister();
|
||||
await sql`
|
||||
DELETE FROM gbrain_cycle_locks
|
||||
WHERE id = ${lockId} AND holder_pid = ${pid}
|
||||
`;
|
||||
// Direct session pool (same rationale as refresh, #1794) + optional
|
||||
// signal so a deadline-bound caller's release can't hang forever on
|
||||
// an exhausted pooler. TTL is the backstop if the DELETE is cancelled.
|
||||
await engine.executeRawDirect(
|
||||
`DELETE FROM gbrain_cycle_locks
|
||||
WHERE id = $1 AND holder_pid = $2`,
|
||||
[lockId, pid],
|
||||
{ signal },
|
||||
);
|
||||
},
|
||||
};
|
||||
}
|
||||
@@ -303,6 +316,11 @@ export async function tryAcquireDbLock(
|
||||
const first = await acquireOnce();
|
||||
if (first) return first;
|
||||
|
||||
// #2750: deadline-bound callers prefer an honest busy result over the
|
||||
// best-effort same-host takeover below, whose inspect/delete/retry calls
|
||||
// are not signal-bounded. The initial upsert already reclaims expired locks.
|
||||
if (opts.signal) return null;
|
||||
|
||||
// v0.42 (#1780 Gap 3): the lock is held and its TTL hasn't expired (the
|
||||
// upsert's ON CONFLICT ... WHERE ttl_expires_at < NOW() returned no row).
|
||||
// If the holder is on THIS host, provably dead, and past the grace window,
|
||||
@@ -796,6 +814,10 @@ export interface WithRefreshingLockOpts {
|
||||
ttlMinutes?: number;
|
||||
/** Heartbeat-fail threshold in ms — abort if SELECT 1 takes longer. Default 30000. */
|
||||
heartbeatTimeoutMs?: number;
|
||||
/** #2750: bound lock acquisition with the caller's deadline signal. */
|
||||
signal?: AbortSignal;
|
||||
/** Fresh cleanup budget for the release DELETE when `signal` is set. Default 5000. */
|
||||
releaseTimeoutMs?: number;
|
||||
}
|
||||
|
||||
/**
|
||||
@@ -815,7 +837,7 @@ export async function withRefreshingLock<T>(
|
||||
// Refresh 6x per TTL window so a missed tick doesn't expire the lock.
|
||||
const refreshIntervalMs = Math.max(15000, (ttlMinutes * 60 * 1000) / 6);
|
||||
|
||||
const handle = await tryAcquireDbLock(engine, lockId, ttlMinutes);
|
||||
const handle = await tryAcquireDbLock(engine, lockId, ttlMinutes, { signal: opts.signal });
|
||||
if (!handle) throw new LockUnavailableError(lockId);
|
||||
|
||||
let healthOk = true;
|
||||
@@ -854,7 +876,13 @@ export async function withRefreshingLock<T>(
|
||||
return await work();
|
||||
} finally {
|
||||
clearInterval(interval);
|
||||
try { await handle.release(); } catch { /* idempotent */ }
|
||||
// #2750: when the caller is deadline-bound, its work signal may already
|
||||
// have fired — release on a FRESH short grace signal so cleanup neither
|
||||
// inherits the spent deadline nor hangs unbounded. TTL is the backstop.
|
||||
const releaseSignal = opts.signal
|
||||
? AbortSignal.timeout(opts.releaseTimeoutMs ?? 5_000)
|
||||
: undefined;
|
||||
try { await handle.release(releaseSignal); } catch { /* idempotent; TTL backstop */ }
|
||||
if (!healthOk) {
|
||||
// Surface that the heartbeat detected backend trouble — caller can
|
||||
// log to the connection-events audit if desired.
|
||||
|
||||
+9
-1
@@ -696,8 +696,16 @@ export interface BrainEngine {
|
||||
* is included in the INSERT column list so ON CONFLICT (source_id, slug)
|
||||
* DO UPDATE actually targets the intended row instead of fabricating a
|
||||
* duplicate at (default, slug). Multi-source brains MUST pass sourceId.
|
||||
*
|
||||
* `opts.signal` (#2750): optional cancellation for deadline-bound writers.
|
||||
* Postgres cancels the in-flight statement; PGLite pre-checks only (query
|
||||
* cancellation is not possible in-process — cooperative abort between calls).
|
||||
*/
|
||||
putPage(slug: string, page: PageInput, opts?: { sourceId?: string }): Promise<Page>;
|
||||
putPage(
|
||||
slug: string,
|
||||
page: PageInput,
|
||||
opts?: { sourceId?: string; signal?: AbortSignal },
|
||||
): Promise<Page>;
|
||||
/**
|
||||
* v0.41.13 (#1309) — identity-based dedup pre-check for the import pipeline.
|
||||
*
|
||||
|
||||
@@ -187,6 +187,7 @@ function buildReceiptFrontmatter(input: ExtractReceiptInput): Record<string, unk
|
||||
export async function writeReceipt(
|
||||
engine: BrainEngine,
|
||||
input: ExtractReceiptInput,
|
||||
opts?: { signal?: AbortSignal },
|
||||
): Promise<{ slug: string; page: Page }> {
|
||||
const slug = receiptSlug(input);
|
||||
const title = `${input.kind} — ${input.round} — ${input.source_id}`;
|
||||
@@ -201,7 +202,7 @@ export async function writeReceipt(
|
||||
compiled_truth,
|
||||
frontmatter,
|
||||
},
|
||||
{ sourceId: input.source_id },
|
||||
{ sourceId: input.source_id, signal: opts?.signal },
|
||||
);
|
||||
|
||||
return { slug, page };
|
||||
|
||||
@@ -70,6 +70,7 @@ function today(): string {
|
||||
export async function upsertExtractRollup(
|
||||
engine: BrainEngine,
|
||||
input: RollupUpsertInput,
|
||||
opts?: { signal?: AbortSignal },
|
||||
): Promise<{ ok: boolean; error?: string }> {
|
||||
const day = input.day ?? today();
|
||||
const cost = input.cost_delta ?? 0;
|
||||
@@ -96,9 +97,12 @@ export async function upsertExtractRollup(
|
||||
rollup_write_failures = extract_rollup_7d.rollup_write_failures + EXCLUDED.rollup_write_failures,
|
||||
updated_at = now()`,
|
||||
[input.kind, input.source_id, day, cost, halts, evalFails, evalPasses, completed, failures],
|
||||
{ signal: opts?.signal },
|
||||
);
|
||||
return { ok: true };
|
||||
} catch (err) {
|
||||
// Signal-bounded callers get the abort surfaced, not a swallowed `ok:false`.
|
||||
if (opts?.signal?.aborted) throw err;
|
||||
const msg = (err as Error).message || String(err);
|
||||
// Don't spam: log once per process per (kind, day) error class.
|
||||
rollupErrorLogOnce(input.kind, day, msg);
|
||||
|
||||
@@ -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;
|
||||
|
||||
@@ -1003,7 +1003,15 @@ export class PGLiteEngine implements BrainEngine {
|
||||
return { slug: r.slug, id: Number(r.id) };
|
||||
}
|
||||
|
||||
async putPage(slug: string, page: PageInput, opts?: { sourceId?: string }): Promise<Page> {
|
||||
async putPage(
|
||||
slug: string,
|
||||
page: PageInput,
|
||||
opts?: { sourceId?: string; signal?: AbortSignal },
|
||||
): Promise<Page> {
|
||||
// #2750: PGLite is in-process WASM — no query cancellation. Pre-check so
|
||||
// an already-fired deadline skips the write; abort is cooperative
|
||||
// between calls (same posture as executeRaw's documented gap).
|
||||
if (opts?.signal?.aborted) throw new DOMException('aborted', 'AbortError');
|
||||
slug = validateSlug(slug);
|
||||
const hash = page.content_hash || contentHash(page);
|
||||
const frontmatter = page.frontmatter || {};
|
||||
|
||||
@@ -72,6 +72,32 @@ function escapeSqlStringLiteral(value: string): string {
|
||||
return value.replace(/'/g, "''");
|
||||
}
|
||||
|
||||
/**
|
||||
* #2750: race a promise against an AbortSignal, detaching the listener once
|
||||
* settled (long-lived drain signals are reused across many calls, so a bare
|
||||
* Promise.race would leak one listener per call). The abandoned promise keeps
|
||||
* running; used only for pool-acquisition waits where that is harmless.
|
||||
*/
|
||||
function waitForSignal<T>(work: Promise<T>, signal?: AbortSignal): Promise<T> {
|
||||
if (!signal) return work;
|
||||
if (signal.aborted) return Promise.reject(new DOMException('aborted', 'AbortError'));
|
||||
return new Promise<T>((resolve, reject) => {
|
||||
let settled = false;
|
||||
const finish = (fn: () => void) => {
|
||||
if (settled) return;
|
||||
settled = true;
|
||||
signal.removeEventListener('abort', onAbort);
|
||||
fn();
|
||||
};
|
||||
const onAbort = () => finish(() => reject(new DOMException('aborted', 'AbortError')));
|
||||
signal.addEventListener('abort', onAbort, { once: true });
|
||||
work.then(
|
||||
(value) => finish(() => resolve(value)),
|
||||
(err) => finish(() => reject(err)),
|
||||
);
|
||||
});
|
||||
}
|
||||
|
||||
export function getPostgresSchema(
|
||||
dims: number = DEFAULT_EMBEDDING_DIMENSIONS,
|
||||
model: string = DEFAULT_EMBEDDING_MODEL,
|
||||
@@ -1061,7 +1087,12 @@ export class PostgresEngine implements BrainEngine {
|
||||
});
|
||||
}
|
||||
|
||||
async putPage(slug: string, page: PageInput, opts?: { sourceId?: string }): Promise<Page> {
|
||||
async putPage(
|
||||
slug: string,
|
||||
page: PageInput,
|
||||
opts?: { sourceId?: string; signal?: AbortSignal },
|
||||
): Promise<Page> {
|
||||
if (opts?.signal?.aborted) throw new DOMException('aborted', 'AbortError');
|
||||
slug = validateSlug(slug);
|
||||
const sql = this.sql;
|
||||
const hash = page.content_hash || contentHash(page);
|
||||
@@ -1096,7 +1127,7 @@ export class PostgresEngine implements BrainEngine {
|
||||
const sourceUri = page.source_uri ?? null;
|
||||
const ingestedVia = page.ingested_via ?? null;
|
||||
const ingestedAt = (sourceKind || sourceUri || ingestedVia) ? new Date() : null;
|
||||
const rows = await sql`
|
||||
const pending = sql`
|
||||
INSERT INTO pages (source_id, slug, type, page_kind, title, compiled_truth, timeline, frontmatter, content_hash, updated_at, effective_date, effective_date_source, import_filename, chunker_version, source_path, source_kind, source_uri, ingested_via, ingested_at)
|
||||
VALUES (${sourceId}, ${slug}, ${page.type}, ${pageKind}, ${page.title}, ${page.compiled_truth}, ${page.timeline || ''}, ${sql.json(frontmatter as Parameters<typeof sql.json>[0])}, ${hash}, now(), ${effectiveDate}, ${effectiveDateSource}, ${importFilename}, COALESCE(${chunkerVersion}::smallint, ${MARKDOWN_CHUNKER_VERSION}), ${sourcePath}, ${sourceKind}, ${sourceUri}, ${ingestedVia}, ${ingestedAt})
|
||||
ON CONFLICT (source_id, slug) DO UPDATE SET
|
||||
@@ -1119,6 +1150,22 @@ export class PostgresEngine implements BrainEngine {
|
||||
ingested_at = COALESCE(EXCLUDED.ingested_at, pages.ingested_at)
|
||||
RETURNING id, source_id, slug, type, title, compiled_truth, timeline, frontmatter, content_hash, created_at, updated_at, effective_date, effective_date_source, import_filename, source_kind, source_uri, ingested_via, ingested_at
|
||||
`;
|
||||
// #2750: cancel the in-flight statement when the caller's deadline fires,
|
||||
// same .cancel() wiring as runUnsafe (postgres.js pending queries).
|
||||
if (opts?.signal) {
|
||||
const signal = opts.signal;
|
||||
const onAbort = () => {
|
||||
try { (pending as unknown as { cancel?: () => void }).cancel?.(); } catch { /* best-effort */ }
|
||||
};
|
||||
signal.addEventListener('abort', onAbort, { once: true });
|
||||
try {
|
||||
const rows = await pending;
|
||||
return rowToPage(rows[0]);
|
||||
} finally {
|
||||
signal.removeEventListener('abort', onAbort);
|
||||
}
|
||||
}
|
||||
const rows = await pending;
|
||||
return rowToPage(rows[0]);
|
||||
}
|
||||
|
||||
@@ -5807,11 +5854,16 @@ export class PostgresEngine implements BrainEngine {
|
||||
params?: unknown[],
|
||||
opts?: { signal?: AbortSignal },
|
||||
): Promise<T[]> {
|
||||
// #2750: an already-fired signal short-circuits BEFORE any pool routing,
|
||||
// and the direct-pool acquisition itself is signal-bounded — under pooler
|
||||
// exhaustion `ddl()` can stall indefinitely, which used to make even a
|
||||
// "bounded" lock release hang past its caller's deadline.
|
||||
if (opts?.signal?.aborted) throw new DOMException('aborted', 'AbortError');
|
||||
// Inside an open transaction, _sql is the reserved tx connection (set via
|
||||
// defineProperty in transaction()); never reroute off it.
|
||||
const inTransaction = this._sql !== null && this.connectionManager?.peekReadPool() !== this._sql;
|
||||
const conn = (!inTransaction && this.connectionManager?.isDualPoolActive())
|
||||
? await this.connectionManager.ddl()
|
||||
? await waitForSignal(this.connectionManager.ddl(), opts?.signal)
|
||||
: this.sql;
|
||||
return this.runUnsafe<T>(conn, sql, params, opts);
|
||||
}
|
||||
|
||||
@@ -17,6 +17,7 @@ import { runPhaseExtractAtoms, parseAtomsResponse } from '../../src/core/cycle/e
|
||||
import { runPhaseSynthesizeConcepts } from '../../src/core/cycle/synthesize-concepts.ts';
|
||||
import { resetPgliteState } from '../helpers/reset-pglite.ts';
|
||||
import type { ChatResult, ChatOpts } from '../../src/core/ai/gateway.ts';
|
||||
import type { BrainEngine } from '../../src/core/engine.ts';
|
||||
|
||||
let engine: PGLiteEngine;
|
||||
|
||||
@@ -177,6 +178,180 @@ describe('v0.41 T5: runPhaseExtractAtoms via stubbed chat', () => {
|
||||
expect((result.details?.failures as unknown[]).length).toBe(1);
|
||||
});
|
||||
|
||||
// ── #2750: caller deadline bounds the phase ────────────────────────────
|
||||
|
||||
test('caller deadline aborts a hung chat before processing the next item', async () => {
|
||||
let calls = 0;
|
||||
const chat = async (opts: ChatOpts) => {
|
||||
calls++;
|
||||
return await new Promise<never>((_resolve, reject) => {
|
||||
const signal = opts.abortSignal;
|
||||
if (!signal) return reject(new Error('missing abort signal'));
|
||||
if (signal.aborted) return reject(signal.reason);
|
||||
signal.addEventListener('abort', () => reject(signal.reason), { once: true });
|
||||
});
|
||||
};
|
||||
const started = Date.now();
|
||||
const result = await runPhaseExtractAtoms(engine, {
|
||||
_transcripts: [
|
||||
{ filePath: '/hung.txt', content: 'a', contentHash: 'hung-a' },
|
||||
{ filePath: '/never.txt', content: 'b', contentHash: 'hung-b' },
|
||||
],
|
||||
_pages: [],
|
||||
_chat: chat as typeof import('../../src/core/ai/gateway.ts').chat,
|
||||
abortSignal: AbortSignal.timeout(25),
|
||||
});
|
||||
expect(Date.now() - started).toBeLessThan(2_000);
|
||||
expect(calls).toBe(1);
|
||||
expect(result.status).toBe('ok');
|
||||
expect(result.details?.deadline_aborted).toBe(true);
|
||||
expect(result.details?.atoms_extracted).toBe(0);
|
||||
expect(result.details?.failures).toEqual([]);
|
||||
});
|
||||
|
||||
test('billable chat usage is counted when the deadline fires as the response resolves', async () => {
|
||||
const controller = new AbortController();
|
||||
const chat = async (opts: ChatOpts): Promise<ChatResult> => {
|
||||
controller.abort(new DOMException('deadline', 'TimeoutError'));
|
||||
return stubChat(`[{"title":"late","atom_type":"insight","body":"b"}]`, {
|
||||
input_tokens: 1_000,
|
||||
output_tokens: 500,
|
||||
})(opts);
|
||||
};
|
||||
const result = await runPhaseExtractAtoms(engine, {
|
||||
_transcripts: [{ filePath: '/late.txt', content: 'a', contentHash: 'late' }],
|
||||
_pages: [],
|
||||
_chat: chat,
|
||||
abortSignal: controller.signal,
|
||||
});
|
||||
expect(result.details?.deadline_aborted).toBe(true);
|
||||
expect(Number(result.details?.estimated_spend_usd)).toBeGreaterThan(0);
|
||||
expect(result.details?.atoms_extracted).toBe(0);
|
||||
});
|
||||
|
||||
test('deadline after partial progress still writes receipt and incomplete rollup', async () => {
|
||||
const controller = new AbortController();
|
||||
let calls = 0;
|
||||
let notifySecondChat!: () => void;
|
||||
const secondChatStarted = new Promise<void>((resolve) => { notifySecondChat = resolve; });
|
||||
const chat = async (opts: ChatOpts): Promise<ChatResult> => {
|
||||
calls++;
|
||||
if (calls === 1) {
|
||||
return stubChat(`[{"title":"committed","atom_type":"insight","body":"b"}]`)(opts);
|
||||
}
|
||||
notifySecondChat();
|
||||
return await new Promise<never>((_resolve, reject) => {
|
||||
const signal = opts.abortSignal;
|
||||
if (!signal) return reject(new Error('missing abort signal'));
|
||||
signal.addEventListener('abort', () => reject(signal.reason), { once: true });
|
||||
});
|
||||
};
|
||||
|
||||
const pending = runPhaseExtractAtoms(engine, {
|
||||
_transcripts: [
|
||||
{ filePath: '/committed.txt', content: 'a', contentHash: 'committed-a' },
|
||||
{ filePath: '/hung.txt', content: 'b', contentHash: 'hung-b' },
|
||||
],
|
||||
_pages: [],
|
||||
_chat: chat,
|
||||
abortSignal: controller.signal,
|
||||
});
|
||||
await secondChatStarted;
|
||||
controller.abort(new DOMException('deadline', 'TimeoutError'));
|
||||
const result = await pending;
|
||||
|
||||
const atoms = await engine.executeRaw<{ n: number }>(
|
||||
`SELECT COUNT(*)::int AS n FROM pages WHERE type = 'atom'`,
|
||||
);
|
||||
const receipts = await engine.executeRaw<{ n: number }>(
|
||||
`SELECT COUNT(*)::int AS n FROM pages WHERE type = 'extract_receipt'`,
|
||||
);
|
||||
const rollups = await engine.executeRaw<{
|
||||
cost_usd: string | number;
|
||||
round_completed_count: string | number;
|
||||
}>(
|
||||
`SELECT cost_usd, round_completed_count
|
||||
FROM extract_rollup_7d
|
||||
WHERE kind = 'atoms' AND source_id = 'default'`,
|
||||
);
|
||||
expect(result.details?.deadline_aborted).toBe(true);
|
||||
expect(atoms[0].n).toBe(1);
|
||||
expect(receipts[0].n).toBe(1);
|
||||
expect(Number(rollups[0].cost_usd)).toBeGreaterThan(0);
|
||||
expect(Number(rollups[0].round_completed_count)).toBe(0);
|
||||
});
|
||||
|
||||
test('bookkeeping runs on a fresh grace signal, not the fired work deadline', async () => {
|
||||
const controller = new AbortController();
|
||||
let putCalls = 0;
|
||||
let receiptSignal: AbortSignal | undefined;
|
||||
let rollupSignal: AbortSignal | undefined;
|
||||
const signalAwareEngine = {
|
||||
executeRaw: async (sql: string, _params?: unknown[], opts?: { signal?: AbortSignal }) => {
|
||||
if (sql.includes('INSERT INTO extract_rollup_7d')) rollupSignal = opts?.signal;
|
||||
return [];
|
||||
},
|
||||
putPage: async (_slug: string, _page: unknown, opts?: { signal?: AbortSignal }) => {
|
||||
putCalls++;
|
||||
if (putCalls === 1) {
|
||||
// Atom write in flight; the work deadline fires before bookkeeping.
|
||||
controller.abort(new DOMException('work deadline', 'TimeoutError'));
|
||||
} else {
|
||||
receiptSignal = opts?.signal;
|
||||
}
|
||||
return {};
|
||||
},
|
||||
} as unknown as BrainEngine;
|
||||
|
||||
const result = await runPhaseExtractAtoms(signalAwareEngine, {
|
||||
_transcripts: [{ filePath: '/one.txt', content: 'a', contentHash: 'one' }],
|
||||
_pages: [],
|
||||
_chat: stubChat(`[{"title":"one","atom_type":"insight","body":"b"}]`),
|
||||
abortSignal: controller.signal,
|
||||
});
|
||||
|
||||
expect(result.details?.atoms_extracted).toBe(1);
|
||||
expect(putCalls).toBe(2); // atom write + receipt write
|
||||
expect(receiptSignal).toBeDefined();
|
||||
expect(receiptSignal).not.toBe(controller.signal);
|
||||
expect(receiptSignal?.aborted).toBe(false);
|
||||
expect(rollupSignal).toBe(receiptSignal);
|
||||
});
|
||||
|
||||
test('caller deadline cancels a hung atom write and stops the phase', async () => {
|
||||
const controller = new AbortController();
|
||||
let notifyWriteStarted!: () => void;
|
||||
const writeStarted = new Promise<void>((resolve) => { notifyWriteStarted = resolve; });
|
||||
let writeCalls = 0;
|
||||
const signalAwareEngine = {
|
||||
executeRaw: async () => [],
|
||||
putPage: async (_slug: string, _page: unknown, opts?: { signal?: AbortSignal }) => {
|
||||
writeCalls++;
|
||||
notifyWriteStarted();
|
||||
return await new Promise<never>((_resolve, reject) => {
|
||||
const signal = opts?.signal;
|
||||
if (!signal) return reject(new Error('missing abort signal'));
|
||||
if (signal.aborted) return reject(signal.reason);
|
||||
signal.addEventListener('abort', () => reject(signal.reason), { once: true });
|
||||
});
|
||||
},
|
||||
} as unknown as BrainEngine;
|
||||
|
||||
const pending = runPhaseExtractAtoms(signalAwareEngine, {
|
||||
_transcripts: [{ filePath: '/hung-write.txt', content: 'a', contentHash: 'hung-write' }],
|
||||
_pages: [],
|
||||
_chat: stubChat(`[{"title":"hung write","atom_type":"insight","body":"b"}]`),
|
||||
abortSignal: controller.signal,
|
||||
});
|
||||
await writeStarted;
|
||||
controller.abort(new DOMException('deadline', 'TimeoutError'));
|
||||
const result = await pending;
|
||||
|
||||
expect(writeCalls).toBe(1);
|
||||
expect(result.details?.deadline_aborted).toBe(true);
|
||||
expect(result.details?.atoms_extracted).toBe(0);
|
||||
});
|
||||
|
||||
// v0.41.2.1 regression case (D9 #14 wording): with _pages:[] and same
|
||||
// _transcripts, all PRE-EXISTING PhaseResult.details fields match
|
||||
// pre-fix values byte-for-byte. The new fields (pages_processed,
|
||||
|
||||
@@ -43,26 +43,135 @@ describe('runExtractAtomsDrain (issue #1678)', () => {
|
||||
expect(batches).toBe(3);
|
||||
});
|
||||
|
||||
it('stops at the wallclock window with remaining > 0', async () => {
|
||||
// SYNC stepping clock: now() #1 sets deadline (0+100=100); the while-check
|
||||
// then sees 50, 50 (two batches), then 999999 → past deadline → stop.
|
||||
const times = [0, 50, 50, 999_999];
|
||||
let ti = 0;
|
||||
const now = () => times[Math.min(ti++, times.length - 1)];
|
||||
it('stops at the wallclock window; remaining is unknown (no post-window count)', async () => {
|
||||
// Each batch consumes 60ms of the 100ms window: two batches fit, the
|
||||
// third boundary check sees 120 ≥ 100 and stops. #2750: after the window
|
||||
// elapses the final countRemaining is SKIPPED (it would overrun the
|
||||
// window), so remaining reports null.
|
||||
let now = 0;
|
||||
const result = await runExtractAtomsDrain(
|
||||
{
|
||||
withLock: passThroughLock,
|
||||
countRemaining: async () => 5, // never drains
|
||||
runBatch: async () => ({ extracted: 1, skipped: 0 }),
|
||||
now,
|
||||
runBatch: async () => {
|
||||
now += 60;
|
||||
return { extracted: 1, skipped: 0 };
|
||||
},
|
||||
now: () => now,
|
||||
},
|
||||
{ windowMs: 100 },
|
||||
);
|
||||
expect(result.stopped).toBe('window');
|
||||
expect(result.remaining).toBe(5);
|
||||
expect(result.remaining).toBeNull();
|
||||
expect(result.batches).toBe(2);
|
||||
});
|
||||
|
||||
it('passes one drain-level deadline signal into count and batch', async () => {
|
||||
const seen: AbortSignal[] = [];
|
||||
const controller = new AbortController();
|
||||
let now = 0;
|
||||
const result = await runExtractAtomsDrain(
|
||||
{
|
||||
withLock: passThroughLock,
|
||||
countRemaining: async (signal) => {
|
||||
seen.push(signal);
|
||||
return 5;
|
||||
},
|
||||
runBatch: async (signal) => {
|
||||
seen.push(signal);
|
||||
now = 100;
|
||||
return { extracted: 1, skipped: 0 };
|
||||
},
|
||||
now: () => now,
|
||||
},
|
||||
{ windowMs: 100, abortSignal: controller.signal },
|
||||
);
|
||||
expect(result.stopped).toBe('window');
|
||||
expect(result.batches).toBe(1);
|
||||
expect(seen.length).toBe(2);
|
||||
expect(seen[0]).toBe(seen[1]);
|
||||
// Combined (timeout + external) signal, not the raw external one.
|
||||
expect(seen[0]).not.toBe(controller.signal);
|
||||
});
|
||||
|
||||
it('aborts a hung backlog count at the window deadline and releases the lock', async () => {
|
||||
let released = false;
|
||||
const result = await runExtractAtomsDrain(
|
||||
{
|
||||
withLock: async (work) => {
|
||||
try { return await work(); }
|
||||
finally { released = true; }
|
||||
},
|
||||
// Hangs until the drain's real-time deadline signal fires (10ms).
|
||||
countRemaining: (signal) => new Promise((_resolve, reject) => {
|
||||
signal.addEventListener('abort', () => reject(signal.reason), { once: true });
|
||||
}),
|
||||
runBatch: async () => ({ extracted: 0, skipped: 0 }),
|
||||
now: () => 0, // injected clock never advances — the SIGNAL must save us
|
||||
},
|
||||
{ windowMs: 10 },
|
||||
);
|
||||
expect(result.stopped).toBe('window');
|
||||
expect(result.remaining).toBeNull();
|
||||
expect(released).toBe(true);
|
||||
});
|
||||
|
||||
it('rethrows external cancellation after releasing the lock', async () => {
|
||||
const controller = new AbortController();
|
||||
let released = false;
|
||||
const pending = runExtractAtomsDrain(
|
||||
{
|
||||
withLock: async (work) => {
|
||||
try { return await work(); }
|
||||
finally { released = true; }
|
||||
},
|
||||
countRemaining: (signal) => new Promise((_resolve, reject) => {
|
||||
signal.addEventListener('abort', () => reject(signal.reason), { once: true });
|
||||
}),
|
||||
runBatch: async () => ({ extracted: 0, skipped: 0 }),
|
||||
now: () => 0,
|
||||
},
|
||||
{ windowMs: 1_000_000, abortSignal: controller.signal },
|
||||
);
|
||||
controller.abort(new DOMException('worker timeout', 'AbortError'));
|
||||
await expect(pending).rejects.toThrow('worker timeout');
|
||||
expect(released).toBe(true);
|
||||
});
|
||||
|
||||
it('classifies a deadline-exhausted zero-progress batch as window, not no_progress', async () => {
|
||||
let now = 0;
|
||||
const result = await runExtractAtomsDrain(
|
||||
{
|
||||
withLock: passThroughLock,
|
||||
countRemaining: async () => 5,
|
||||
runBatch: async () => {
|
||||
now = 100; // batch consumed the whole window and returned nothing
|
||||
return { extracted: 0, skipped: 0 };
|
||||
},
|
||||
now: () => now,
|
||||
},
|
||||
{ windowMs: 100 },
|
||||
);
|
||||
expect(result.stopped).toBe('window');
|
||||
expect(result.batches).toBe(1);
|
||||
});
|
||||
|
||||
it('bounds a hung lock acquisition with the drain deadline signal', async () => {
|
||||
const started = Date.now();
|
||||
await expect(runExtractAtomsDrain(
|
||||
{
|
||||
withLock: (_work, signal) => new Promise((_resolve, reject) => {
|
||||
signal.addEventListener('abort', () => reject(signal.reason), { once: true });
|
||||
}),
|
||||
countRemaining: async () => 1,
|
||||
runBatch: async () => ({ extracted: 0, skipped: 0 }),
|
||||
now: Date.now,
|
||||
},
|
||||
{ windowMs: 10 },
|
||||
)).rejects.toThrow();
|
||||
expect(Date.now() - started).toBeLessThan(1_000);
|
||||
});
|
||||
|
||||
it('stops on a zero-progress batch (no hot loop)', async () => {
|
||||
let batches = 0;
|
||||
const result = await runExtractAtomsDrain(
|
||||
@@ -133,4 +242,17 @@ describe('shared wiring helper holds the cycle lock (5A)', () => {
|
||||
expect(src).toContain('cycleLockIdFor(opts.sourceId)');
|
||||
expect(src).toContain('withRefreshingLock(engine, lockId');
|
||||
});
|
||||
|
||||
// #2750: the deadline signal must reach the phase, the backlog count, AND
|
||||
// the lock wrapper — and the transcript path (brainDir) must stay wired
|
||||
// exactly as the routine callers expect (PR #2752 takeover reverted its
|
||||
// unsanctioned transcript-suppression scope change).
|
||||
it('threads the drain deadline signal through phase, count, and lock', () => {
|
||||
const jobsSrc = readFileSync(join(import.meta.dir, '../src/commands/jobs.ts'), 'utf8');
|
||||
expect(src).toContain('abortSignal: signal');
|
||||
expect(src).toContain('countExtractAtomsBacklog(engine, extractionSourceId, signal)');
|
||||
expect(src).toContain('brainDir: opts.brainDir');
|
||||
expect(src).not.toContain('_transcripts');
|
||||
expect(jobsSrc).toContain('abortSignal: job.signal');
|
||||
});
|
||||
});
|
||||
|
||||
@@ -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.
|
||||
|
||||
Vendored
+9
-6
@@ -24,15 +24,18 @@ import type { BrainEngine } from '../../src/core/engine.ts';
|
||||
// Mock engine: healthCheck() calls engine.executeRaw; return empty rows so
|
||||
// the query path exercises without needing Postgres.
|
||||
//
|
||||
// #1849: start() now acquires the queue-scoped DB singleton lock via
|
||||
// tryAcquireDbLock, which uses the postgres `sql` tagged-template escape hatch.
|
||||
// The stub returns a single row from every call so acquire succeeds (length 1
|
||||
// → acquired) and refresh/release are no-ops. Each spawned runner is a fresh
|
||||
// process, so there's no cross-test lock state to clean up.
|
||||
// #1849: start() acquires the queue-scoped DB singleton lock via
|
||||
// tryAcquireDbLock. #2750 routed the acquire upsert through engine.executeRaw
|
||||
// (signal-boundable) and release through engine.executeRawDirect, so the
|
||||
// stub returns a single row from the lock upsert (length 1 → acquired) and
|
||||
// empty rows everywhere else. Each spawned runner is a fresh process, so
|
||||
// there's no cross-test lock state to clean up.
|
||||
const sqlStub = (..._args: unknown[]) => Promise.resolve([{ id: 'supervisor-lock' }]);
|
||||
const mockEngine: Partial<BrainEngine> = {
|
||||
kind: 'postgres' as const,
|
||||
executeRaw: async () => [],
|
||||
executeRaw: async (query: string) =>
|
||||
query.includes('gbrain_cycle_locks') ? [{ id: 'supervisor-lock' }] : [],
|
||||
executeRawDirect: async () => [],
|
||||
sql: sqlStub,
|
||||
} as unknown as BrainEngine;
|
||||
|
||||
|
||||
@@ -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]]' });
|
||||
});
|
||||
});
|
||||
|
||||
@@ -98,14 +98,39 @@ describe('PostgresEngine.executeRawDirect — routing decision (PR #1816)', () =
|
||||
});
|
||||
|
||||
test('already-aborted signal short-circuits with AbortError before routing the query', async () => {
|
||||
const readConn = fakeSql('read');
|
||||
let unsafeCalls = 0;
|
||||
let ddlCalls = 0;
|
||||
const readConn: FakeSql = { unsafe: async () => { unsafeCalls++; return []; } };
|
||||
const directConn = fakeSql('direct');
|
||||
const engine = makeEngine({ dualPoolActive: true, readConn, directConn });
|
||||
const e = engine as unknown as { connectionManager: { ddl: () => Promise<FakeSql> } };
|
||||
e.connectionManager.ddl = async () => { ddlCalls++; return directConn; };
|
||||
|
||||
const ac = new AbortController();
|
||||
ac.abort();
|
||||
await expect(
|
||||
engine.executeRawDirect('UPDATE minion_jobs SET x=1', [], { signal: ac.signal }),
|
||||
).rejects.toThrow(/abort/i);
|
||||
// #2750: short-circuits BEFORE pool routing — no ddl(), no unsafe().
|
||||
expect(ddlCalls).toBe(0);
|
||||
expect(unsafeCalls).toBe(0);
|
||||
});
|
||||
|
||||
test('#2750: signal bounds a stalled direct-pool acquisition before unsafe starts', async () => {
|
||||
let unsafeCalls = 0;
|
||||
const readConn: FakeSql = { unsafe: async () => { unsafeCalls++; return []; } };
|
||||
const directConn = fakeSql('direct');
|
||||
const engine = makeEngine({ dualPoolActive: true, readConn, directConn });
|
||||
const e = engine as unknown as { connectionManager: { ddl: () => Promise<FakeSql> } };
|
||||
e.connectionManager.ddl = () => new Promise<FakeSql>(() => {}); // pooler exhausted: never resolves
|
||||
|
||||
const started = Date.now();
|
||||
await expect(engine.executeRawDirect(
|
||||
'DELETE FROM gbrain_cycle_locks',
|
||||
[],
|
||||
{ signal: AbortSignal.timeout(10) },
|
||||
)).rejects.toThrow(/abort/i);
|
||||
expect(Date.now() - started).toBeLessThan(1_000);
|
||||
expect(unsafeCalls).toBe(0);
|
||||
});
|
||||
});
|
||||
|
||||
Reference in New Issue
Block a user