Compare commits

..
Author SHA1 Message Date
Garry TanandClaude Fable 5 72b9e9333f fix(extract): resolve cross-directory wikilinks via sync-consistent slugification (#1964)
Raw Obsidian wikilink paths ([[llm-wiki/entities/AI 3.0]]) never matched
sync-slugified slugs (llm-wiki/entities/ai-3.0) on either extraction path.

- FS path: resolveSlug now slugifies each candidate (slugifyPath, the same
  function sync uses) when the raw path-equality check misses, in both the
  direct join and the ancestor walk. Dir-qualified wikilinks resolve as
  typed edges without the global_basename flag.
- DB path: extractPageLinks resolves dir-qualified generic wikilinks by
  slugifying the path and matching by exact slug or path suffix against
  the basename index — regardless of global_basename (the flag guards
  bare-name cross-dir ambiguity, which doesn't apply to dir-qualified
  paths). A same-tail page in a different directory can no longer be the
  only candidate and is filtered out.

Fixes #1964

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-21 14:57:58 -07:00
12 changed files with 126 additions and 232 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
+15 -5
View File
@@ -43,7 +43,7 @@ import {
} from '../core/link-extraction.ts';
import { createProgress } from '../core/progress.ts';
import { getCliOptions, cliOptsToProgressOptions } from '../core/cli-options.ts';
import { pathToSlug, pruneDir, isSyncable } from '../core/sync.ts';
import { pathToSlug, slugifyPath, pruneDir, isSyncable } from '../core/sync.ts';
// v0.41.18.0: withRetry + isRetryableConnError + WithRetryOpts moved to
// src/core/retry.ts as the canonical primitive. Engine methods
// (addLinksBatch/addTimelineEntriesBatch/upsertChunks) now self-retry via
@@ -269,14 +269,24 @@ export function extractMarkdownLinks(content: string): { name: string; relTarget
export function resolveSlug(fileDir: string, relTarget: string, allSlugs: Set<string>): string | null {
const targetNoExt = relTarget.endsWith('.md') ? relTarget.slice(0, -3) : relTarget;
const s1 = join(fileDir, targetNoExt);
if (allSlugs.has(s1)) return s1;
// Issue #1964: wikilinks carry raw Obsidian paths (`[[llm-wiki/entities/AI 3.0]]`)
// but allSlugs holds sync-slugified slugs (`llm-wiki/entities/ai-3.0`). Try the
// raw candidate first (back-compat), then the sync-consistent slugified form.
const hit = (candidate: string): string | null => {
if (allSlugs.has(candidate)) return candidate;
const slugified = slugifyPath(candidate);
if (slugified !== candidate && allSlugs.has(slugified)) return slugified;
return null;
};
const s1 = hit(join(fileDir, targetNoExt));
if (s1) return s1;
const parts = fileDir.split('/').filter(Boolean);
for (let strip = 1; strip <= parts.length; strip++) {
const ancestor = parts.slice(0, parts.length - strip).join('/');
const candidate = ancestor ? join(ancestor, targetNoExt) : targetNoExt;
if (allSlugs.has(candidate)) return candidate;
const candidate = hit(ancestor ? join(ancestor, targetNoExt) : targetNoExt);
if (candidate) return candidate;
}
return null;
+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',
});
}
+20 -4
View File
@@ -14,6 +14,7 @@
import type { BrainEngine } from './engine.ts';
import type { PageType } from './types.ts';
import { ensureWellFormed } from './text-safe.ts';
import { slugifyPath } from './sync.ts';
/**
* v0.42.7 — link-extraction version stamp. Bump this ISO timestamp whenever the
@@ -482,14 +483,29 @@ export async function extractPageLinks(
// pre-v0.40.8.2 behavior of dropping bare wikilinks outside
// DIR_PATTERN.
if (ref.needsResolution) {
if (!opts.globalBasename || typeof resolver.resolveBasenameMatches !== 'function') {
continue;
}
if (typeof resolver.resolveBasenameMatches !== 'function') continue;
// Issue #972 (codex): resolve by the wikilink TARGET (ref.slug — the
// text inside `[[...]]` before any `|`), NOT the display alias
// (ref.name = match[2]). `[[struktura|the project]]` must resolve
// `struktura`, not "the project". The display text is for context only.
const matches = await resolver.resolveBasenameMatches(ref.slug);
//
// Issue #1964: a dir-qualified wikilink (`[[llm-wiki/entities/AI 3.0]]`)
// carries a raw Obsidian path while page slugs are sync-slugified
// (`llm-wiki/entities/ai-3.0`). Slugify the path the same way sync does,
// then match by exact slug or path-suffix (wiki-root-relative authoring).
// This runs regardless of global_basename — it's dir-qualified, so the
// cross-dir false-positive risk the flag guards against doesn't apply.
// Mirrors the FS path's resolveSlug ancestor walk. Bare `[[name]]`
// wikilinks still require the global_basename flag.
let matches: string[] = [];
const slugified = ref.slug.includes('/') ? slugifyPath(ref.slug) : '';
if (slugified.includes('/')) {
const tail = slugified.slice(slugified.lastIndexOf('/') + 1);
matches = (await resolver.resolveBasenameMatches(tail))
.filter(m => m === slugified || m.endsWith(`/${slugified}`));
} else if (opts.globalBasename) {
matches = await resolver.resolveBasenameMatches(ref.slug);
}
if (matches.length === 0) continue;
const idx = content.indexOf(ref.slug);
const context = idx >= 0 ? excerpt(content, idx, 240) : ref.name;
-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));
+27
View File
@@ -389,6 +389,33 @@ describe('resolveSlugAll', () => {
});
});
// ─── issue #1964: cross-directory wikilinks — slug/path mismatch ──────────
describe('issue #1964: raw Obsidian wikilink paths resolve to sync-slugified slugs', () => {
test('resolveSlug slugifies the candidate (sync-consistent), no flag needed', () => {
const all = new Set(['llm-wiki/entities/ai-3.0']);
// Wikilink literal `[[llm-wiki/entities/AI 3.0]]` — spaces + uppercase.
expect(resolveSlug('llm-wiki/notes', 'llm-wiki/entities/AI 3.0.md', all))
.toBe('llm-wiki/entities/ai-3.0');
});
test('resolveSlug slugifies raw (unslugified) fileDir too', () => {
const all = new Set(['llm-wiki/entities/ai-3.0']);
// fileDir comes from dirname(relPath) — the raw on-disk directory.
expect(resolveSlug('LLM Wiki/Notes', 'entities/AI 3.0.md', all))
.toBe('llm-wiki/entities/ai-3.0');
});
test('extractLinksFromFile resolves cross-directory wikilink with flag OFF as a typed edge', async () => {
const allSlugs = new Set(['llm-wiki/entities/ai-3.0', 'llm-wiki/notes/roadmap']);
const content = '---\ntitle: Roadmap\ntype: concept\n---\n\nSee [[llm-wiki/entities/AI 3.0]].\n';
const links = await extractLinksFromFile(content, 'llm-wiki/notes/roadmap.md', allSlugs);
expect(links.map(l => l.to_slug)).toEqual(['llm-wiki/entities/ai-3.0']);
// Dir-qualified path resolution is exact, NOT the basename fallback.
expect(links[0].link_type).not.toBe('wikilink_basename');
});
});
describe('issue #972 repro: bare wikilinks resolve when flag is on', () => {
// End-to-end: reproduces the issue's exact repro inside a tempdir +
// PGLite, then asserts edge count under both flag states.
+42
View File
@@ -9,6 +9,8 @@ import {
parseTimelineEntries,
isAutoLinkEnabled,
FRONTMATTER_LINK_MAP,
buildBasenameIndex,
queryBasenameIndex,
type SlugResolver,
} from '../src/core/link-extraction.ts';
import type { BrainEngine } from '../src/core/engine.ts';
@@ -424,6 +426,46 @@ describe('extractPageLinks', () => {
expect(strk!.linkType).toBe('wikilink_basename');
});
// ─── issue #1964: dir-qualified wikilinks with raw Obsidian paths ────────
test('#1964: dir-qualified wikilink resolves via sync-consistent slugification (flag OFF)', async () => {
// `[[llm-wiki/entities/AI 3.0]]` is a raw Obsidian path; the page slug
// is the sync-slugified `llm-wiki/entities/ai-3.0`. Must resolve WITHOUT
// global_basename (it's dir-qualified) and must NOT leak to a same-tail
// page in a different directory.
const resolver: SlugResolver = {
resolve: async () => null,
resolveBasenameMatches: async (name) =>
name === 'ai-3.0' ? ['other/ai-3.0', 'llm-wiki/entities/ai-3.0'] : [],
};
const { candidates } = await extractPageLinks(
'llm-wiki/notes/roadmap',
'See [[llm-wiki/entities/AI 3.0]] for the model.',
{}, 'concept', resolver,
// opts.globalBasename omitted (= false) — path is dir-qualified
);
expect(candidates.map(c => c.targetSlug)).toEqual(['llm-wiki/entities/ai-3.0']);
expect(candidates[0].linkType).toBe('wikilink_basename');
expect(candidates[0].linkSource).toBe('wikilink-resolved');
});
test('#1964: path-suffix match resolves wiki-root-relative paths against a real index', async () => {
// Author writes `[[llm-wiki/entities/AI 3.0]]` but the brain nests the
// wiki under a vault dir. Suffix match rescues it; queried through the
// REAL basename index so the tail-key lookup is exercised end to end.
const idx = buildBasenameIndex(['vault/llm-wiki/entities/ai-3.0', 'people/ai-3.0']);
const resolver: SlugResolver = {
resolve: async () => null,
resolveBasenameMatches: async (name) => queryBasenameIndex(idx, name),
};
const { candidates } = await extractPageLinks(
'vault/llm-wiki/notes/roadmap',
'See [[llm-wiki/entities/AI 3.0]].',
{}, 'concept', resolver,
);
expect(candidates.map(c => c.targetSlug)).toEqual(['vault/llm-wiki/entities/ai-3.0']);
});
test('opts.skipFrontmatter suppresses the frontmatter pass', async () => {
// Real resolver shape that WOULD resolve frontmatter source: too,
// but skipFrontmatter blocks the path entirely.
@@ -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);
});
});