Compare commits

..
Author SHA1 Message Date
Garry TanandClaude Fable 5 a42352081c test(extract): pin the version-arm stamp floor with an explicit regression test
The floor in extractStaleFromDB was only covered incidentally — the #1768
test's updated_at (2026-06-02) fell below the bumped VERSION_TS, but its
comment still says the date was chosen to sit ABOVE the watermark. A future
date 'repair' there would silently drop floor coverage. This test pins it
directly: pre-watermark page clears after --stale and stays cleared.
Verified fail-without-fix against master's extract.ts.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-22 11:59:09 -07:00
Garry TanandClaude Fable 5 070f4c5678 fix(extract): floor --stale stamp at LINK_EXTRACTOR_VERSION_TS so version bumps don't create permanently-stale pages
The version-ts bump in this PR exposed a latent conflict: extractStaleFromDB
stamps links_extracted_at = the page's read updated_at (#1768 µs fix), but a
page last edited BEFORE the new LINK_EXTRACTOR_VERSION_TS then lands below the
version watermark and the 'links_extracted_at < versionTs' arm re-flags it
stale on every run — an infinite re-extraction loop. Stamp
max(updated_at, versionTs); versionTs is always a past release date, so the
D4 concurrent-edit race guard still holds.

Fixes the test/extract-stale.test.ts CI failure on this branch.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-22 10:56:38 -07:00
Garry TanandClaude Fable 5 4b2df89935 fix(extract): resolve path-style wikilinks outside DIR_PATTERN + add ops/ to whitelist (#2576 bug 2)
- Add ops to DIR_PATTERN so [[ops/services/...]] wikilinks and bare
  ops/... slug refs are recognized as qualified entity references.
- queryBasenameIndex (the shared basename matcher behind
  resolveBasenameMatches, the FS resolver, and the doctor check) now
  falls back to the path tail when a path-style ref misses — before,
  normalizeBasename stripped slashes into a garbage key that could
  never hit the tail-keyed index.
- Bump LINK_EXTRACTOR_VERSION_TS so extract --stale re-sweeps
  previously-stamped pages with the new extraction logic.

Bugs 1+3 of #2576 are covered by PR #2717 (--stale nullResolver).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-21 14:33:45 -07:00
9 changed files with 63 additions and 139 deletions
+9 -1
View File
@@ -1743,7 +1743,15 @@ async function extractStaleFromDB(
// `page.updated_at.toISOString()` — the JS Date is ms-truncated, so the
// µs-precision DB updated_at stayed strictly greater and the page never
// cleared on Postgres. Stamping the exact value makes them equal.
processedRefs.push({ slug: page.slug, source_id: page.source_id, extractedAt: page.updated_at_iso });
//
// Version-arm floor: a page last edited BEFORE LINK_EXTRACTOR_VERSION_TS
// would otherwise be stamped below the version watermark and stay
// permanently stale (`links_extracted_at < versionTs` re-fires every run).
// Stamp max(updated_at, versionTs) — versionTs is always a past release
// date, so a concurrent edit's now() still exceeds the stamp and D4 holds.
// Tie at ms precision picks updated_at_iso (its µs ≥ versionTs's .000000).
const stampTs = new Date(page.updated_at_iso) >= new Date(versionTs) ? page.updated_at_iso : versionTs;
processedRefs.push({ slug: page.slug, source_id: page.source_id, extractedAt: stampTs });
}
// Flush NON-swallowing (CDX-4): a throw here propagates out of the sweep so
+1 -5
View File
@@ -142,16 +142,12 @@ export async function runOnboard(engine: BrainEngine, args: string[]): Promise<v
// --auto path: runs through the T2 library orchestrator. Hooks emit CLI
// progress to stderr; the final result lands as JSON on stdout (or human
// summary). extraRemediations (gathered above from runAllOnboardChecks)
// is threaded into the runner so the onboard-check remediations
// (extract-ner, extract-timeline-from-meetings, etc.) reach the planner
// — the same wiring the --check path uses above.
// summary).
const result = await runRemediation(
engine,
{
targetScore,
maxUsd,
extraRemediations,
// --auto --yes opts into the prompt_required tier too; library
// doesn't distinguish auto_apply vs prompt_required, it just runs
// every remediation in the plan. The plan-building side (T12 render)
+13 -4
View File
@@ -28,7 +28,7 @@ import { ensureWellFormed } from './text-safe.ts';
* OR updated_at > links_extracted_at`. It is an ISO-8601 string (NOT a number) —
* the column is TIMESTAMPTZ and the predicate binds it as `::timestamptz`.
*/
export const LINK_EXTRACTOR_VERSION_TS = '2026-05-31T00:00:00Z';
export const LINK_EXTRACTOR_VERSION_TS = '2026-07-21T00:00:00Z';
// ─── Entity references ──────────────────────────────────────────
@@ -80,10 +80,10 @@ export type LinkResolutionType = 'qualified' | 'unqualified';
* Directory prefix whitelist. These are the top-level slug dirs the extractor
* recognizes as entity references. Upstream canonical + our extensions:
* - Gbrain canonical: people, companies, meetings, concepts, deal, civic, project, source, media, yc, projects
* - Our domain extensions: tech, finance, personal, openclaw (domain-organized wikis)
* - Our domain extensions: tech, finance, personal, openclaw, ops (domain-organized wikis)
* - Our entity prefix: entities (we kept some legacy entities/projects/ pages)
*/
const DIR_PATTERN = '(?:people|companies|meetings|concepts|deal|civic|project|projects|source|media|yc|tech|finance|personal|openclaw|entities)';
const DIR_PATTERN = '(?:people|companies|meetings|concepts|deal|civic|project|projects|source|media|yc|tech|finance|personal|openclaw|entities|ops)';
/**
* Match `[Name](path)` markdown links pointing to entity directories.
@@ -865,7 +865,16 @@ export function queryBasenameIndex(idx: Map<string, string[]>, name: string): st
if (!name || typeof name !== 'string') return [];
const trimmed = name.trim();
if (!trimmed) return [];
const hit = idx.get(trimmed) ?? idx.get(trimmed.toLowerCase()) ?? idx.get(normalizeBasename(trimmed));
let hit = idx.get(trimmed) ?? idx.get(trimmed.toLowerCase()) ?? idx.get(normalizeBasename(trimmed));
// Issue #2576 bug 2: path-style refs (`runbooks/2026-05-01-x`) from dirs
// outside DIR_PATTERN reach here, but normalizeBasename strips slashes
// into a garbage key (`runbooks2026-05-01-x`) that can never hit the
// tail-keyed index. Fall back to the path tail so qualified refs resolve
// by basename like everything else.
if (!hit && trimmed.includes('/')) {
const tail = trimmed.slice(trimmed.lastIndexOf('/') + 1).trim();
if (tail) hit = idx.get(tail) ?? idx.get(tail.toLowerCase()) ?? idx.get(normalizeBasename(tail));
}
return hit ? [...hit].sort(basenameSort) : [];
}
+1 -1
View File
@@ -4957,7 +4957,7 @@ const run_onboard: Operation = {
// typo, the underlying queue.add would reject. Defense-in-depth.
const result = await runRemediation(
ctx.engine,
{ targetScore, maxUsd, extraRemediations: allowedExtras },
{ targetScore, maxUsd },
{},
);
+3 -10
View File
@@ -66,10 +66,9 @@ export async function runRemediation(
} = await import('../remediation-checkpoint.ts');
const ctx = await loadRecommendationContext(engine);
const extraRemediations = opts.extraRemediations ?? [];
// Pre-flight ceiling check via the shared plan computation.
const initialPlan = await computeRemediationPlan(engine, { targetScore, extraRemediations });
const initialPlan = await computeRemediationPlan(engine, { targetScore });
if (initialPlan.target_unreachable) {
hooks.onTargetUnreachable?.(targetScore, initialPlan.max_reachable_score);
return {
@@ -88,7 +87,7 @@ export async function runRemediation(
}
const initialHealth = await engine.getHealth();
let recs: RemediationStep[] = computeRecommendations(initialHealth, ctx, extraRemediations)
let recs: RemediationStep[] = computeRecommendations(initialHealth, ctx)
.filter((r) => r.status === 'remediable');
if (recs.length === 0) {
hooks.onNothingToDo?.(initialHealth.brain_score, targetScore);
@@ -306,13 +305,7 @@ export async function runRemediation(
// steps with bumped retry suffix (D1).
if (recs.length === 0 || stepCount >= maxJobs) break;
const freshHealth = await engine.getHealth();
// Extras carry a static status:'remediable' — a fresh health snapshot
// never ages them out the way health-derived steps drop. Filter out
// ids this run already processed (any terminal status), or the recheck
// would resubmit completed extras every iteration, forever.
const processedIds = new Set(submitted.map((s) => s.id));
const pendingExtras = extraRemediations.filter((r) => !processedIds.has(r.id));
recs = computeRecommendations(freshHealth, ctx, pendingExtras).filter((r) => r.status === 'remediable');
recs = computeRecommendations(freshHealth, ctx).filter((r) => r.status === 'remediable');
}
};
-10
View File
@@ -63,16 +63,6 @@ export interface RemediationOpts {
resumePlanHash?: string;
/** Whether to attempt resume at all (default false). */
resume?: boolean;
/**
* Caller-supplied RemediationStep entries threaded into the planner.
* Mirrors RemediationPlanOpts.extraRemediations so onboard's --apply
* --auto path (and MCP run_onboard auto modes) forward the same
* onboard-check remediations the --check path already passes through
* computeRemediationPlan. Without this the runner saw only generic
* brain_score remediations and reported "Nothing to do" whenever the
* only applicable work was an extra (e.g. extract-ner).
*/
extraRemediations?: RemediationStep[];
}
/**
+18
View File
@@ -209,6 +209,24 @@ describe('gbrain extract --stale', () => {
expect(usRows[0]?.eq).toBe(true);
});
test('version-arm floor: page edited BEFORE LINK_EXTRACTOR_VERSION_TS clears after --stale (issue #2576 bug 3)', async () => {
// A page whose updated_at predates the version watermark used to be
// stamped at its updated_at (< versionTs), so the version arm re-fired
// every run — permanently stale. The sweep now floors the stamp at
// versionTs. (The #1768 test above also covers this since the v0.42.x
// VERSION_TS bump moved its date below the watermark, but this pins the
// behavior explicitly so a date "repair" there can't drop coverage.)
await engine.putPage('people/alice', personPage('Alice'));
await engine.executeRaw(`UPDATE pages SET updated_at = '2000-01-01T00:00:00Z' WHERE slug = 'people/alice'`);
expect(await engine.countStalePagesForExtraction({ versionTs: LINK_EXTRACTOR_VERSION_TS })).toBe(1);
await runExtract(engine, ['--stale']);
// Pre-floor this stayed 1 forever (stamp < versionTs → version arm re-fires).
expect(await engine.countStalePagesForExtraction({ versionTs: LINK_EXTRACTOR_VERSION_TS })).toBe(0);
await runExtract(engine, ['--stale']);
expect(await engine.countStalePagesForExtraction({ versionTs: LINK_EXTRACTOR_VERSION_TS })).toBe(0);
});
test('CDX-4 (D2): a link-flush throw aborts the sweep and leaves pages UNSTAMPED', async () => {
await engine.putPage('people/alice', personPage('Alice'));
await engine.putPage('companies/acme', companyPage('Acme', '[Alice](people/alice) founded [Acme](companies/acme).'));
+18
View File
@@ -140,6 +140,15 @@ describe('extractEntityRefs', () => {
expect(wikiRefs[0].needsResolution).toBe(true);
});
test('recognizes ops/ qualified wikilinks (issue #2576 bug 2)', () => {
// `ops` was missing from DIR_PATTERN, so [[ops/...]] fell through to
// the generic 2c pass (needsResolution) instead of being a real ref.
const refs = extractEntityRefs('Deployed via [[ops/services/pointer-agent]].');
expect(refs.length).toBe(1);
expect(refs[0].slug).toBe('ops/services/pointer-agent');
expect(refs[0].needsResolution).toBeUndefined();
});
test('skips qualified-syntax tokens (those belong to 2a)', () => {
// [[wiki:topics/ai]] looks like 2a's qualified shape — even though
// it wouldn't satisfy DIR_PATTERN, 2c must not claim it either
@@ -1069,6 +1078,15 @@ describe('makeResolver — fallback chain', () => {
]);
});
test('resolveBasenameMatches: path-style ref falls back to the tail (issue #2576 bug 2)', async () => {
// normalizeBasename strips slashes, so `runbooks/2026-05-01-pointer-agent`
// used to normalize to a garbage key that never hit the tail-keyed index.
const engine = makeFakeEngineWithSlugs(['ops/changes/2026-05-01-pointer-agent']);
const r = makeResolver(engine);
expect(await r.resolveBasenameMatches!('runbooks/2026-05-01-pointer-agent'))
.toEqual(['ops/changes/2026-05-01-pointer-agent']);
});
test('resolveBasenameMatches: case-insensitive fallback', async () => {
const engine = makeFakeEngineWithSlugs(['companies/fast-weigh']);
const r = makeResolver(engine);
-108
View File
@@ -1,108 +0,0 @@
// test/remediation-run-extras.serial.test.ts
// Regression for PR #2161 takeover: `gbrain onboard --apply --auto` dropped
// onboard-check extraRemediations. Two distinct halves of the bug:
// 1. runRemediation built the pre-flight plan + initial recs WITHOUT the
// extras, so an extras-only plan reported "Nothing to do".
// 2. The D7 mid-run recheck rebuilt recs WITHOUT the extras after every
// completed step, so with 2+ plannable steps all remaining extras were
// dropped after step 1. The recheck must also filter out extras this
// run already processed — extras carry static status:'remediable', so
// unfiltered threading would resubmit completed extras forever.
//
// SERIAL: mock.module (queue + wait-for-completion stubs, R2) + GBRAIN_HOME
// env mutation so checkpoint files land in a tmpdir, not ~/.gbrain.
import { describe, expect, test, beforeAll, afterAll, mock } from 'bun:test';
import { mkdtempSync, rmSync } from 'node:fs';
import { tmpdir } from 'node:os';
import { join } from 'node:path';
import { PGLiteEngine } from '../src/core/pglite-engine.ts';
import { makeRemediationStep } from '../src/core/remediation-step.ts';
// Stub the Minion queue: every submitted job is immediately 'completed'.
// runRemediation only calls queue.add + waitForCompletion(queue, id).
let nextJobId = 1;
const submittedJobs: Array<{ name: string }> = [];
mock.module('../src/core/minions/queue.ts', () => ({
MinionQueue: class {
async add(name: string) {
submittedJobs.push({ name });
return { id: nextJobId++, status: 'completed' };
}
},
}));
mock.module('../src/core/minions/wait-for-completion.ts', () => ({
waitForCompletion: async () => ({ status: 'completed' }),
}));
let engine: PGLiteEngine;
let home: string;
const prevHome = process.env.GBRAIN_HOME;
beforeAll(async () => {
home = mkdtempSync(join(tmpdir(), 'gbrain-remextras-'));
process.env.GBRAIN_HOME = home;
engine = new PGLiteEngine();
await engine.connect({});
await engine.initSchema();
}, 120_000);
afterAll(async () => {
await engine.disconnect();
if (prevHome === undefined) delete process.env.GBRAIN_HOME;
else process.env.GBRAIN_HOME = prevHome;
rmSync(home, { recursive: true, force: true });
});
function extra(id: string, job: string) {
return makeRemediationStep({
id,
job,
params: {},
severity: 'medium',
est_seconds: 5,
est_usd_cost: 0,
rationale: 'synthetic onboard-check extra',
status: 'remediable',
});
}
describe('runRemediation extraRemediations threading', () => {
test('extras-only plan runs BOTH extras and terminates (no Nothing-to-do, no resubmit loop)', async () => {
// Empty PGLite brain → zero health-derived recommendations. Without the
// fix, half 1 makes this run return submitted: [] via onNothingToDo.
// With only half 1 (the original PR #2161 diff), the mid-run recheck
// drops the second extra after step 1 — submitted has 1 entry, not 2.
const { runRemediation } = await import('../src/core/remediation/run.ts');
let nothingToDo = false;
const result = await runRemediation(
engine,
{
targetScore: 1,
extraRemediations: [
extra('onboard.extract_ner', 'extract-ner'),
extra('onboard.extract_timeline', 'extract-timeline-from-meetings'),
],
// Safety bound: an unfiltered recheck would resubmit completed
// extras forever; maxJobs turns that regression into a fast fail
// (extra count > 1 below) instead of a hung test.
maxJobs: 5,
},
{ onNothingToDo: () => { nothingToDo = true; } },
);
expect(nothingToDo).toBe(false);
const ids = result.submitted.map((s) => s.id);
expect(ids).toContain('onboard.extract_ner');
expect(ids).toContain('onboard.extract_timeline');
// Each extra ran exactly once — the recheck must not re-plan extras the
// run already processed.
expect(ids.filter((i) => i === 'onboard.extract_ner').length).toBe(1);
expect(ids.filter((i) => i === 'onboard.extract_timeline').length).toBe(1);
expect(result.submitted.every((s) => s.status === 'completed')).toBe(true);
expect(submittedJobs.map((j) => j.name).sort()).toEqual([
'extract-ner',
'extract-timeline-from-meetings',
]);
});
});