Compare commits

..
Author SHA1 Message Date
Garry TanandClaude Fable 5 921048827a fix(remediation): pass LINK_EXTRACTOR_VERSION_TS to the extraction-lag gate
countExtractionLag omitted versionTs, so its predicate diverged from the
counter it claims to share with doctor's links_extraction_lag check and
the extract --stale walk: pages stamped before an extractor version bump
(links_extracted_at < LINK_EXTRACTOR_VERSION_TS) lagged for doctor and
extract but never tripped the sync.repo/extract.all gate. Pass the stamp;
pin the version-bump arm with a backdated-page test (fails without it).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-22 10:53:55 -07:00
0dff84b16a fix(remediation): gate sync/extract recs on real extraction lag, refresh at D7 recheck
Takeover of #2363. The sync.repo/extract.all recommendations gated on
health.stale_pages — a proxy (updated_at predates newest timeline entry)
that stopped meaning anything after migration v10 dropped the trigger
behind it. Gate them on the honest counter instead:
engine.countStalePagesForExtraction, the same staleness `gbrain extract
--stale` and doctor's links_extraction_lag use.

On top of the original PR, two repairs:

- runRemediation loads RecommendationContext once, but the D7 per-step
  recheck reused the frozen extractionLagPages — a completed sync/extract
  step could never clear the gate, so the pipeline re-fired every recheck
  until maxJobs. The recheck now refreshes the gate alongside getHealth
  via the shared countExtractionLag() helper (extracted into
  remediation/context.ts). Pinned by
  test/remediation-run-d7-refresh.serial.test.ts (serial: mock.module).
- autopilot builds its own RecommendationContext by hand; without wiring,
  it would silently never fire sync.repo/extract.all again. It now
  populates extractionLagPages from the same helper.

Co-authored-by: DarkNightForge <DarkNightForge@users.noreply.github.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-21 15:06:34 -07:00
15 changed files with 229 additions and 327 deletions
+4
View File
@@ -686,6 +686,7 @@ 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();
@@ -877,6 +878,9 @@ 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
+3 -22
View File
@@ -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})`);
+26 -8
View File
@@ -146,6 +146,16 @@ 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. */
@@ -192,20 +202,28 @@ export function computeRecommendations(
const source = ctx.sourceId ?? 'default';
// ---------------------------------------------------------------------
// sync.repo — fires when sync hasn't run recently OR pages are stale
// 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.
// ---------------------------------------------------------------------
if (ctx.repoPath && health.stale_pages > 0) {
const extractionLag = ctx.extractionLagPages ?? 0;
if (ctx.repoPath && extractionLag > 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: health.stale_pages > 50 ? 'high' : 'medium',
est_seconds: Math.min(600, 30 + health.stale_pages * 0.5),
severity: extractionLag > 50 ? 'high' : 'medium',
est_seconds: Math.min(600, 30 + extractionLag * 0.5),
est_usd_cost: 0, // sync is fs+DB only
depends_on: [],
rationale: `${health.stale_pages} stale page${health.stale_pages === 1 ? '' : 's'} on disk`,
rationale: `Sync before extracting ${extractionLag} page${extractionLag === 1 ? '' : 's'} with stale link/timeline edges`,
status: 'remediable',
});
}
@@ -237,7 +255,7 @@ 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 && health.stale_pages > 0 ? ['sync.repo'] : [],
depends_on: ctx.repoPath && extractionLag > 0 ? ['sync.repo'] : [],
rationale: `${health.missing_embeddings} chunk${health.missing_embeddings === 1 ? '' : 's'} invisible to vector search`,
status: 'remediable',
});
@@ -267,7 +285,7 @@ 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 && health.stale_pages > 0) {
if (ctx.repoPath && extractionLag > 0) {
const params = { mode: 'all', dir: ctx.repoPath };
out.push({
id: 'extract.all',
@@ -278,7 +296,7 @@ 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 from fresh pages',
rationale: `Materialize link + timeline edges for ${extractionLag} page${extractionLag === 1 ? '' : 's'} with stale extraction`,
status: 'remediable',
});
}
-12
View File
@@ -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. */
-16
View File
@@ -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;
+3 -36
View File
@@ -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;
+25
View File
@@ -8,6 +8,7 @@
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
@@ -68,5 +69,29 @@ 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;
}
}
+7 -2
View File
@@ -16,7 +16,7 @@ import {
computeRecommendations,
} from '../brain-score-recommendations.ts';
import type { RemediationStep } from '../remediation-step.ts';
import { loadRecommendationContext } from './context.ts';
import { countExtractionLag, 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');
const ctx = await loadRecommendationContext(engine);
let ctx = await loadRecommendationContext(engine);
// Pre-flight ceiling check via the shared plan computation.
const initialPlan = await computeRemediationPlan(engine, { targetScore });
@@ -305,6 +305,11 @@ 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
@@ -1423,6 +1423,15 @@ 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
+9 -12
View File
@@ -119,13 +119,12 @@ describe('computeRecommendations', () => {
expect(recs.find((r) => r.id === 'embed.stale')).toBeUndefined();
});
test('stale pages + dead links produce sync + backlinks + extract', () => {
test('extraction lag + 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 });
const recs = computeRecommendations(health, { repoPath: '/brain', embeddingProviderConfigured: true, extractionLagPages: 25 });
const ids = recs.map((r) => r.id);
expect(ids).toContain('sync.repo');
expect(ids).toContain('backlinks.fix');
@@ -133,18 +132,17 @@ describe('computeRecommendations', () => {
});
test('extract.all depends on sync.repo (D14: stable ids)', () => {
const health = makeHealth({ stale_pages: 10 });
const recs = computeRecommendations(health, { repoPath: '/brain', embeddingProviderConfigured: true });
const health = makeHealth();
const recs = computeRecommendations(health, { repoPath: '/brain', embeddingProviderConfigured: true, extractionLagPages: 10 });
const extract = recs.find((r) => r.id === 'extract.all');
expect(extract?.depends_on).toContain('sync.repo');
});
test('embed.stale depends on sync.repo when sync also needed', () => {
test('embed.stale depends on sync.repo when extraction also needed', () => {
const health = makeHealth({
stale_pages: 10,
missing_embeddings: 100,
});
const recs = computeRecommendations(health, { repoPath: '/brain', embeddingProviderConfigured: true });
const recs = computeRecommendations(health, { repoPath: '/brain', embeddingProviderConfigured: true, extractionLagPages: 10 });
const embed = recs.find((r) => r.id === 'embed.stale');
expect(embed?.depends_on).toContain('sync.repo');
});
@@ -159,9 +157,9 @@ describe('computeRecommendations', () => {
test('severity ordering: critical before high before medium', () => {
const health = makeHealth({
missing_embeddings: 100, // critical
stale_pages: 80, // high
});
const recs = computeRecommendations(health, { repoPath: '/brain', embeddingProviderConfigured: true });
// extractionLagPages > 50 → sync.repo fires at 'high' severity.
const recs = computeRecommendations(health, { repoPath: '/brain', embeddingProviderConfigured: true, extractionLagPages: 80 });
const critIdx = recs.findIndex((r) => r.severity === 'critical');
const highIdx = recs.findIndex((r) => r.severity === 'high');
expect(critIdx).toBeLessThan(highIdx);
@@ -170,11 +168,10 @@ 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' };
const ctx = { repoPath: '/brain', embeddingProviderConfigured: true, sourceId: 'default', extractionLagPages: 10 };
const run1 = computeRecommendations(health, ctx);
const run2 = computeRecommendations(health, ctx);
expect(JSON.stringify(run1)).toBe(JSON.stringify(run2));
-34
View File
@@ -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);
});
});
-12
View File
@@ -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.
-173
View File
@@ -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]]' });
});
});
@@ -0,0 +1,62 @@
// 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);
});
});
@@ -0,0 +1,81 @@
// 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);
});
});