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
12 changed files with 80 additions and 228 deletions
-4
View File
@@ -686,7 +686,6 @@ export async function runAutopilot(engine: BrainEngine, args: string[]) {
try {
const { MinionQueue } = await import('../core/minions/queue.ts');
const { computeRecommendations, embeddingProviderConfigured, HOSTED_EMBED_KEY_CONFIG } = await import('../core/brain-score-recommendations.ts');
const { countExtractionLag } = await import('../core/remediation/context.ts');
const queue = new MinionQueue(engine);
const slotMs = Math.floor(Date.now() / (baseInterval * 1000)) * baseInterval * 1000;
const slot = new Date(slotMs).toISOString();
@@ -878,9 +877,6 @@ export async function runAutopilot(engine: BrainEngine, args: string[]) {
return !!(process.env[envVar] || (cfgField ? embedKeyCfg[cfgField] : undefined));
}),
hasChatApiKey: !!(process.env.ANTHROPIC_API_KEY || await engine.getConfig('anthropic_api_key')),
// Real extraction-lag gate for sync.repo/extract.all — same counter
// loadRecommendationContext uses (replaces the health.stale_pages proxy).
extractionLagPages: await countExtractionLag(engine),
};
// v0.41.18.0 (A5 + A19 + A22, T15): consult onboard recommendations
// ALONGSIDE doctor's brain-score recommendations. Onboard's 4 new
+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
+8 -26
View File
@@ -146,16 +146,6 @@ export interface RecommendationContext {
chatModel?: string;
/** Whether the chat provider has a usable API key. */
hasChatApiKey?: boolean;
/**
* Count of pages needing link/timeline extraction — the SAME staleness the
* `gbrain extract --stale` walk and doctor's `links_extraction_lag` check use
* (`engine.countStalePagesForExtraction`). Gates the sync→extract pipeline
* (sync.repo / extract.all). Replaces the old `health.stale_pages` gate, which
* counted "pages whose updated_at predates their newest timeline entry" — a
* proxy that broke when the updated_at-on-timeline-insert trigger was dropped
* (migration v10) and never reflected real extraction work.
*/
extractionLagPages?: number;
}
/** Triage result for one check. */
@@ -202,28 +192,20 @@ export function computeRecommendations(
const source = ctx.sourceId ?? 'default';
// ---------------------------------------------------------------------
// sync.repo + extract.all — the materialization pipeline, gated on the REAL
// extraction lag (pages whose link/timeline edges are stale), NOT on the
// legacy `health.stale_pages` proxy. `extractionLagPages` comes from the same
// counter the `extract --stale` walk + doctor's `links_extraction_lag` use, so
// the recommendation can only fire when running extract will actually reduce
// it (and clear the rec). See RecommendationContext.extractionLagPages.
// sync.repo is the prerequisite: re-sync so pages are current before extract
// materializes their edges.
// sync.repo — fires when sync hasn't run recently OR pages are stale
// ---------------------------------------------------------------------
const extractionLag = ctx.extractionLagPages ?? 0;
if (ctx.repoPath && extractionLag > 0) {
if (ctx.repoPath && health.stale_pages > 0) {
const params = { repoPath: ctx.repoPath, sourceId: ctx.sourceId, noEmbed: true };
out.push({
id: 'sync.repo',
job: 'sync',
params,
idempotency_key: idemKey(source, 'sync', params),
severity: extractionLag > 50 ? 'high' : 'medium',
est_seconds: Math.min(600, 30 + extractionLag * 0.5),
severity: health.stale_pages > 50 ? 'high' : 'medium',
est_seconds: Math.min(600, 30 + health.stale_pages * 0.5),
est_usd_cost: 0, // sync is fs+DB only
depends_on: [],
rationale: `Sync before extracting ${extractionLag} page${extractionLag === 1 ? '' : 's'} with stale link/timeline edges`,
rationale: `${health.stale_pages} stale page${health.stale_pages === 1 ? '' : 's'} on disk`,
status: 'remediable',
});
}
@@ -255,7 +237,7 @@ export function computeRecommendations(
est_seconds: Math.min(3600, 5 + health.missing_embeddings * 0.05),
est_usd_cost,
// sync should run first so embed sees fresh pages.
depends_on: ctx.repoPath && extractionLag > 0 ? ['sync.repo'] : [],
depends_on: ctx.repoPath && health.stale_pages > 0 ? ['sync.repo'] : [],
rationale: `${health.missing_embeddings} chunk${health.missing_embeddings === 1 ? '' : 's'} invisible to vector search`,
status: 'remediable',
});
@@ -285,7 +267,7 @@ export function computeRecommendations(
// Triggered when sync.repo fires (because sync was set to noEmbed:true,
// and noExtract:true after T5 lands → extract job is the materializer).
// ---------------------------------------------------------------------
if (ctx.repoPath && extractionLag > 0) {
if (ctx.repoPath && health.stale_pages > 0) {
const params = { mode: 'all', dir: ctx.repoPath };
out.push({
id: 'extract.all',
@@ -296,7 +278,7 @@ export function computeRecommendations(
est_seconds: Math.min(600, 30 + health.page_count * 0.01),
est_usd_cost: 0,
depends_on: ['sync.repo'],
rationale: `Materialize link + timeline edges for ${extractionLag} page${extractionLag === 1 ? '' : 's'} with stale extraction`,
rationale: 'Materialize link + timeline edges from fresh pages',
status: 'remediable',
});
}
+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) : [];
}
-25
View File
@@ -8,7 +8,6 @@
import type { BrainEngine } from '../engine.ts';
import type { RecommendationContext } from '../brain-score-recommendations.ts';
import { LINK_EXTRACTOR_VERSION_TS } from '../link-extraction.ts';
// Re-export so consumers can `import { RecommendationContext } from '../remediation'`
// — the canonical RecommendationContext type still lives in
@@ -69,29 +68,5 @@ export async function loadRecommendationContext(
embeddingDimensions,
embeddingProviderConfigured: embeddingConfigured,
hasChatApiKey: !!(process.env.ANTHROPIC_API_KEY || fileCfg?.anthropic_api_key),
extractionLagPages: await countExtractionLag(engine),
};
}
/**
* Real extraction-lag count — the SAME staleness `gbrain extract --stale`
* processes (engine.countStalePagesForExtraction with
* versionTs=LINK_EXTRACTOR_VERSION_TS, matching doctor's links_extraction_lag
* check — without versionTs, pages stamped before an extractor version bump
* would lag for doctor/extract but never trip this gate). Drives the
* sync→extract recommendation pipeline; replaces the legacy
* `health.stale_pages` proxy that no longer reflected real extraction work
* after the v10 trigger drop.
*
* Shared by loadRecommendationContext AND the D7 per-step recheck in
* runRemediation — the recheck MUST refresh this gate alongside getHealth,
* or a completed extract step keeps re-firing off the frozen initial count.
*/
export async function countExtractionLag(engine: BrainEngine): Promise<number> {
try {
return await engine.countStalePagesForExtraction({ versionTs: LINK_EXTRACTOR_VERSION_TS });
} catch {
/* counter unavailable (very old brain / mid-migration) — treat as 0 */
return 0;
}
}
+2 -7
View File
@@ -16,7 +16,7 @@ import {
computeRecommendations,
} from '../brain-score-recommendations.ts';
import type { RemediationStep } from '../remediation-step.ts';
import { countExtractionLag, loadRecommendationContext } from './context.ts';
import { loadRecommendationContext } from './context.ts';
import { computeRemediationPlan } from './plan.ts';
import type {
RemediationHooks,
@@ -65,7 +65,7 @@ export async function runRemediation(
clearRemediationCheckpoint,
} = await import('../remediation-checkpoint.ts');
let ctx = await loadRecommendationContext(engine);
const ctx = await loadRecommendationContext(engine);
// Pre-flight ceiling check via the shared plan computation.
const initialPlan = await computeRemediationPlan(engine, { targetScore });
@@ -305,11 +305,6 @@ export async function runRemediation(
// steps with bumped retry suffix (D1).
if (recs.length === 0 || stepCount >= maxJobs) break;
const freshHealth = await engine.getHealth();
// Refresh the extraction-lag gate alongside health: ctx was loaded once
// before the loop, and a completed sync/extract step is exactly what
// drives the count down. Reusing the frozen initial count would re-fire
// sync.repo/extract.all every recheck until maxJobs.
ctx = { ...ctx, extractionLagPages: await countExtractionLag(engine) };
recs = computeRecommendations(freshHealth, ctx).filter((r) => r.status === 'remediable');
}
};
-9
View File
@@ -1423,15 +1423,6 @@ export interface BrainStats {
export interface BrainHealth {
page_count: number;
embed_coverage: number;
/**
* LEGACY proxy: count of pages whose `updated_at` predates their newest
* timeline entry. This bumped meaningfully only while a trigger updated
* `pages.updated_at` on timeline insert; that trigger was dropped in
* migration v10, so the metric no longer reflects real "needs work" state.
* NO LONGER gates remediations — the sync→extract pipeline now gates on
* `RecommendationContext.extractionLagPages` (the real extraction-lag from
* `countStalePagesForExtraction`). Retained for the CLI health line + back-compat.
*/
stale_pages: number;
/**
* Islanded pages — zero inbound AND zero outbound links. A hub page
+12 -9
View File
@@ -119,12 +119,13 @@ describe('computeRecommendations', () => {
expect(recs.find((r) => r.id === 'embed.stale')).toBeUndefined();
});
test('extraction lag + dead links produce sync + backlinks + extract', () => {
test('stale pages + dead links produce sync + backlinks + extract', () => {
const health = makeHealth({
stale_pages: 25,
dead_links: 8,
brain_score: 70,
});
const recs = computeRecommendations(health, { repoPath: '/brain', embeddingProviderConfigured: true, extractionLagPages: 25 });
const recs = computeRecommendations(health, { repoPath: '/brain', embeddingProviderConfigured: true });
const ids = recs.map((r) => r.id);
expect(ids).toContain('sync.repo');
expect(ids).toContain('backlinks.fix');
@@ -132,17 +133,18 @@ describe('computeRecommendations', () => {
});
test('extract.all depends on sync.repo (D14: stable ids)', () => {
const health = makeHealth();
const recs = computeRecommendations(health, { repoPath: '/brain', embeddingProviderConfigured: true, extractionLagPages: 10 });
const health = makeHealth({ stale_pages: 10 });
const recs = computeRecommendations(health, { repoPath: '/brain', embeddingProviderConfigured: true });
const extract = recs.find((r) => r.id === 'extract.all');
expect(extract?.depends_on).toContain('sync.repo');
});
test('embed.stale depends on sync.repo when extraction also needed', () => {
test('embed.stale depends on sync.repo when sync also needed', () => {
const health = makeHealth({
stale_pages: 10,
missing_embeddings: 100,
});
const recs = computeRecommendations(health, { repoPath: '/brain', embeddingProviderConfigured: true, extractionLagPages: 10 });
const recs = computeRecommendations(health, { repoPath: '/brain', embeddingProviderConfigured: true });
const embed = recs.find((r) => r.id === 'embed.stale');
expect(embed?.depends_on).toContain('sync.repo');
});
@@ -157,9 +159,9 @@ describe('computeRecommendations', () => {
test('severity ordering: critical before high before medium', () => {
const health = makeHealth({
missing_embeddings: 100, // critical
stale_pages: 80, // high
});
// extractionLagPages > 50 → sync.repo fires at 'high' severity.
const recs = computeRecommendations(health, { repoPath: '/brain', embeddingProviderConfigured: true, extractionLagPages: 80 });
const recs = computeRecommendations(health, { repoPath: '/brain', embeddingProviderConfigured: true });
const critIdx = recs.findIndex((r) => r.severity === 'critical');
const highIdx = recs.findIndex((r) => r.severity === 'high');
expect(critIdx).toBeLessThan(highIdx);
@@ -168,10 +170,11 @@ describe('computeRecommendations', () => {
// D6 #5 — THE critical regression test for the agent contract.
test('D6 #5: determinism — same input twice produces identical output', () => {
const health = makeHealth({
stale_pages: 10,
missing_embeddings: 50,
dead_links: 3,
});
const ctx = { repoPath: '/brain', embeddingProviderConfigured: true, sourceId: 'default', extractionLagPages: 10 };
const ctx = { repoPath: '/brain', embeddingProviderConfigured: true, sourceId: 'default' };
const run1 = computeRecommendations(health, ctx);
const run2 = computeRecommendations(health, ctx);
expect(JSON.stringify(run1)).toBe(JSON.stringify(run2));
+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);
@@ -1,62 +0,0 @@
// test/remediation-context-extraction-lag.test.ts
//
// Pins the v-next fix: the sync→extract remediation pipeline gates on REAL
// extraction lag, not the legacy `health.stale_pages` proxy (which counted
// "updated_at predates newest timeline entry" — meaningless after the v10
// trigger drop). loadRecommendationContext now populates `extractionLagPages`
// from `engine.countStalePagesForExtraction` — the SAME counter the
// `gbrain extract --stale` walk and doctor's `links_extraction_lag` use — so a
// recommendation can only fire when running extract will actually reduce it.
import { afterAll, beforeAll, describe, expect, it } from 'bun:test';
import { PGLiteEngine } from '../src/core/pglite-engine.ts';
import { loadRecommendationContext } from '../src/core/remediation/context.ts';
let engine: PGLiteEngine;
beforeAll(async () => {
engine = new PGLiteEngine();
await engine.connect({});
await engine.initSchema();
});
afterAll(async () => {
await engine.disconnect();
});
describe('loadRecommendationContext — extractionLagPages wiring', () => {
it('is 0 on an empty brain (nothing to extract)', async () => {
const ctx = await loadRecommendationContext(engine);
expect(ctx.extractionLagPages).toBe(0);
});
it('reflects the real extraction-lag count once a page needs extraction', async () => {
// A freshly-imported page has links_extracted_at = NULL, which the canonical
// countStalePagesForExtraction predicate counts as stale-for-extraction.
await engine.putPage('p0', {
title: 'p0',
type: 'note' as never,
compiled_truth: 'body that is long enough to pass any minimum-length guards in the codebase',
timeline: '',
frontmatter: {},
source_path: 'p0.md',
});
const ctx = await loadRecommendationContext(engine);
expect(ctx.extractionLagPages).toBeGreaterThan(0);
});
it('counts pages stamped before LINK_EXTRACTOR_VERSION_TS (version-bump arm)', async () => {
// Backdate p0 so BOTH the NULL arm and the updated_at arm are quiet:
// updated_at < links_extracted_at, but links_extracted_at predates the
// extractor version stamp. doctor's links_extraction_lag and
// `extract --stale` both count this page; the remediation gate must too.
await engine.executeRaw(
`UPDATE pages SET updated_at = '2020-01-01T00:00:00Z'::timestamptz,
links_extracted_at = '2020-01-02T00:00:00Z'::timestamptz
WHERE slug = 'p0'`,
[],
);
const ctx = await loadRecommendationContext(engine);
expect(ctx.extractionLagPages).toBeGreaterThan(0);
});
});
@@ -1,81 +0,0 @@
// test/remediation-run-d7-refresh.serial.test.ts
//
// Pins the D7-recheck half of the extraction-lag gate fix: runRemediation
// loads RecommendationContext ONCE before the step loop, and the per-step
// recheck (D7) must REFRESH ctx.extractionLagPages alongside getHealth.
// Without the refresh, a completed sync/extract step keeps re-firing off
// the frozen initial count — the plan never converges and the loop burns
// steps until maxJobs.
//
// SERIAL (R2): uses top-level mock.module for the minion queue +
// wait-for-completion so no real worker is needed — mocks leak across
// files in a shard process, so this file must run in its own process.
import { describe, expect, mock, test } from 'bun:test';
// The fake brain: sync.repo clears the extraction lag when it "runs"
// (today's sync materializes link/timeline edges; extract.all is the
// explicit re-materializer). The frozen-ctx bug makes runRemediation
// ignore that and resubmit sync.repo on every D7 recheck.
let extractionLag = 25;
const submittedJobs: string[] = [];
mock.module('../src/core/minions/queue.ts', () => ({
MinionQueue: class {
constructor(_engine: unknown) {}
async add(job: string): Promise<{ id: number }> {
submittedJobs.push(job);
if (job === 'sync' || job === 'extract') extractionLag = 0;
return { id: submittedJobs.length };
}
},
}));
mock.module('../src/core/minions/wait-for-completion.ts', () => ({
waitForCompletion: async () => ({ status: 'completed' }),
}));
const health = () => ({
page_count: 100,
embed_coverage: 1.0,
stale_pages: 0, // legacy proxy stays 0 — the real counter drives the gate
orphan_pages: 0,
missing_embeddings: 0,
brain_score: 70,
dead_links: 0,
link_coverage: 1.0,
timeline_coverage: 1.0,
most_connected: [],
embed_coverage_score: 35,
link_density_score: 25,
timeline_coverage_score: 15,
no_orphans_score: 15,
no_dead_links_score: 10,
});
const fakeEngine = {
kind: 'pglite' as const,
getHealth: async () => health(),
getConfig: async (key: string) =>
key === 'sync.repo_path' ? '/tmp/brain-example' : null,
countStalePagesForExtraction: async () => extractionLag,
};
describe('runRemediation D7 recheck — extraction-lag gate refresh', () => {
test('a completed materializer step clears the gate; the pipeline is not resubmitted', async () => {
const { runRemediation } = await import('../src/core/remediation/run.ts');
const result = await runRemediation(
// Only the methods the orchestrator touches are needed.
fakeEngine as never,
{ targetScore: 0, maxJobs: 6 },
);
// Frozen-ctx bug: extractionLagPages stays 25 forever, so every D7
// recheck re-introduces the sync/extract pipeline and the loop burns
// all 6 maxJobs. With the refresh, the plan converges after the first
// completed step: no step id is ever submitted twice.
const ids = result.submitted.map((s) => s.id);
expect(new Set(ids).size).toBe(ids.length);
expect(submittedJobs.length).toBeLessThan(3);
expect(extractionLag).toBe(0);
});
});