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>

src/cli.ts

@@ -808,20 +808,12 @@ async function makeContext(engine: BrainEngine, params: Record<string, unknown>)
   // 'default'. Wrapped in try/catch so a doctor / single-source brain that
   // never set up sources still returns 'default' silently.
   let sourceId: string | undefined;
-  // #2561: when the source resolved via a NON-explicit tier (path-match /
-  // brain default / sole-non-default / seed default), unqualified search-shaped
-  // reads span every `config.federated = true` source. Computed here (the
-  // trusted local boundary) and consumed by federatedSearchScope in
-  // operations.ts, which additionally gates on ctx.remote === false.
-  let localFederated: string[] | undefined;
   try {
-    const { resolveSourceWithTier, localFederatedSourceIds } = await import('./core/source-resolver.ts');
+    const { resolveSourceId } = await import('./core/source-resolver.ts');
     // params.source is set when a CLI flag was parsed for the op (rare; most
     // CLI ops don't take --source). Falls through to env/dotfile/path-match.
     const explicit = (params.source as string | undefined) ?? null;
-    const resolved = await resolveSourceWithTier(engine, explicit);
-    sourceId = resolved.source_id;
-    localFederated = await localFederatedSourceIds(engine, resolved.source_id, resolved.tier);
+    sourceId = await resolveSourceId(engine, explicit);
   } catch {
     // Source resolution failed (e.g. sources table doesn't exist on a fresh
     // pre-init brain). Leave sourceId unset; engine read methods fall through
@@ -842,7 +834,6 @@ async function makeContext(engine: BrainEngine, params: Record<string, unknown>)
     // table). Matches dispatch.ts's auto-fill so the contract holds across
     // every transport.
     sourceId: sourceId ?? 'default',
-    ...(localFederated ? { localFederatedSourceIds: localFederated } : {}),
   };
 }
 

src/commands/autopilot.ts

@@ -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

src/core/brain-score-recommendations.ts

@@ -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',
     });
   }

src/core/operations.ts

@@ -424,23 +424,6 @@ export interface OperationContext {
    * satisfied even on single-source brains.
    */
   sourceId: string;
-  /**
-   * #2561 — federated read scope for UNQUALIFIED local CLI reads.
-   *
-   * Set ONLY by the local CLI's context builder (src/cli.ts makeContext), and
-   * only when the source resolved via a non-explicit tier (local_path /
-   * brain_default / sole_non_default / seed_default — NOT --source, NOT
-   * GBRAIN_SOURCE, NOT a .gbrain-source dotfile). Contains the resolved
-   * source first, then every other `config.federated = true` source, so an
-   * unqualified `gbrain search "X"` spans federated sources as
-   * docs/guides/multi-source-brains.md promises.
-   *
-   * Consumed exclusively by `federatedSearchScope` and ONLY when
-   * `ctx.remote === false` — a remote caller's scope stays governed by
-   * `ctx.auth.allowedSources` / scalar `ctx.sourceId` (source-isolation
-   * invariant, fail-closed).
-   */
-  localFederatedSourceIds?: string[];
 }
 
 /**
@@ -556,45 +539,6 @@ export function resolveRequestedScope(
   return sourceScopeOpts(ctx);
 }
 
-/**
- * #2561 — source scope for the search-shaped read ops (`search`, `query`).
- *
- * Delegates to `resolveRequestedScope` (the single trust+grant resolver), then
- * widens an UNQUALIFIED trusted-local scalar scope to the CLI-computed
- * federated set (`ctx.localFederatedSourceIds`, resolved source first). This is
- * what makes `sources add --federated` mean something for local search: a
- * federated source participates in unqualified `gbrain search "X"` results.
- *
- * The expansion NEVER applies when:
- *   - the caller is not strictly trusted-local (`ctx.remote !== false`) —
- *     remote scope stays grant-governed (fail-closed source isolation);
- *   - a per-call `source_id` was passed (explicit wins, including `__all__`);
- *   - the resolver already produced a federated array (OAuth grant);
- *   - the CLI resolved the source from an explicit signal (--source / env /
- *     dotfile) — makeContext leaves `localFederatedSourceIds` unset then.
- *
- * Deliberately NOT inside `sourceScopeOpts`: code-intel ops collapse a
- * multi-element scope to an error (`resolveCodeIntelScope`), and non-search
- * reads (get_page, get_links, …) keep their long-standing scalar behavior.
- */
-export function federatedSearchScope(
-  ctx: OperationContext,
-  sourceIdParam?: string,
-): { sourceId?: string; sourceIds?: string[] } {
-  const scope = resolveRequestedScope(ctx, sourceIdParam);
-  if (
-    ctx.remote === false &&
-    sourceIdParam === undefined &&
-    scope.sourceId !== undefined &&
-    scope.sourceIds === undefined &&
-    ctx.localFederatedSourceIds !== undefined &&
-    ctx.localFederatedSourceIds.length > 1
-  ) {
-    return { sourceIds: ctx.localFederatedSourceIds };
-  }
-  return scope;
-}
-
 /**
  * Code-intel adapter for `resolveRequestedScope`. Graph traversal
  * (code_callers/code_callees/code_blast/code_flow) is single-source by design —
@@ -1504,8 +1448,7 @@ const search: Operation = {
     const queryText = p.query as string;
     const limit = (p.limit as number) || 20;
     const offset = (p.offset as number) || 0;
-    // #2561: unqualified trusted-local search spans federated sources.
-    const scope = federatedSearchScope(ctx);
+    const scope = sourceScopeOpts(ctx);
 
     // T4/D5 — per-call mode honored ONLY for trusted/local callers so a remote
     // OAuth client can't escalate to the costly tokenmax bundle. Local + unknown
@@ -1667,9 +1610,7 @@ const query: Operation = {
     // is spread into BOTH the image-similarity searchVector path and the text
     // hybridSearch path below, so both honor the same grant.
     const sourceIdParam = typeof p.source_id === 'string' ? p.source_id : undefined;
-    // #2561: unqualified trusted-local query spans federated sources (per-call
-    // source_id / remote grants still resolve through resolveRequestedScope).
-    const querySourceScope = federatedSearchScope(ctx, sourceIdParam);
+    const querySourceScope = resolveRequestedScope(ctx, sourceIdParam);
 
     // v0.27.1: image-similarity branch. Bypasses hybridSearch (which is
     // text-only); embeds the image via embedMultimodal and runs a direct

src/core/remediation/context.ts

@@ -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;
+  }
+}

src/core/remediation/run.ts

@@ -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');
     }
   };

src/core/source-resolver.ts

@@ -353,45 +353,6 @@ export async function resolveSourceWithTier(
   return { source_id: 'default', tier: 'seed_default' };
 }
 
-/**
- * #2561 — compute the federated read scope for an UNQUALIFIED local CLI call.
- *
- * `sources add --federated` promises that a `config.federated = true` source
- * "participates in unqualified `gbrain search` results"
- * (docs/guides/multi-source-brains.md). This helper turns that promise into a
- * scope: given the resolved source and WHICH tier resolved it, return
- * `[resolvedSource, ...other federated source ids]` — or `undefined` when the
- * expansion must not apply:
- *
- *   - explicit tiers (`flag` / `env` / `dotfile`): the user named a source;
- *     scalar scope stands (that IS the qualified case);
- *   - no other federated source exists: keep the scalar fast path unchanged.
- *
- * Archived sources are excluded (same rationale as pickSoleNonDefaultSource);
- * the archived column is v34+, so fall back to the un-archived query on older
- * brains. Callers put the result on `OperationContext.localFederatedSourceIds`
- * — consumed only by `federatedSearchScope` and only when `remote === false`.
- */
-export async function localFederatedSourceIds(
-  engine: BrainEngine,
-  sourceId: string,
-  tier: SourceTier,
-): Promise<string[] | undefined> {
-  if (tier === 'flag' || tier === 'env' || tier === 'dotfile') return undefined;
-  let rows: Array<{ id: string }>;
-  try {
-    rows = await engine.executeRaw<{ id: string }>(
-      `SELECT id FROM sources WHERE config->>'federated' = 'true' AND archived = false ORDER BY id`,
-    );
-  } catch {
-    rows = await engine.executeRaw<{ id: string }>(
-      `SELECT id FROM sources WHERE config->>'federated' = 'true' ORDER BY id`,
-    );
-  }
-  const ids = [sourceId, ...rows.map((r) => r.id).filter((id) => id !== sourceId)];
-  return ids.length > 1 ? ids : undefined;
-}
-
 /** Exposed for tests. */
 export const __testing = {
   readDotfileWalk,

src/core/types.ts

@@ -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

test/brain-score-recommendations.test.ts

@@ -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));

test/local-federated-search-scope.test.ts

@@ -1,154 +0,0 @@
-/**
- * #2561 — sources.config.federated participates in UNQUALIFIED local CLI
- * search/query.
- *
- * Pre-fix: the local CLI always emitted a scalar `{sourceId}` scope (required
- * field, auto-filled 'default'), so a source registered with
- * `gbrain sources add --federated` was invisible to an unqualified
- * `gbrain search "X"` — contradicting docs/guides/multi-source-brains.md
- * ("Source participates in unqualified `gbrain search` results").
- *
- * Fix: the CLI context builder computes `ctx.localFederatedSourceIds`
- * (resolved source + every other federated source) whenever the source
- * resolved via a NON-explicit tier; `federatedSearchScope` widens the scalar
- * scope to that set for the `search` / `query` ops — trusted-local only
- * (`ctx.remote === false`), never for remote callers, never when a per-call
- * `source_id` or an explicit --source/env/dotfile was given.
- */
-import { describe, test, expect, beforeAll, afterAll } from 'bun:test';
-import { PGLiteEngine } from '../src/core/pglite-engine.ts';
-import { localFederatedSourceIds } from '../src/core/source-resolver.ts';
-import {
-  federatedSearchScope,
-  operations,
-  type OperationContext,
-} from '../src/core/operations.ts';
-
-let engine: PGLiteEngine;
-const search = operations.find((o) => o.name === 'search')!;
-
-function ctxOf(overrides: Partial<OperationContext> = {}): OperationContext {
-  return {
-    engine: engine as any,
-    config: {} as any,
-    logger: console as any,
-    dryRun: false,
-    remote: false,
-    sourceId: 'default',
-    ...overrides,
-  };
-}
-
-beforeAll(async () => {
-  engine = new PGLiteEngine();
-  await engine.connect({});
-  await engine.initSchema();
-  // Seeded 'default' source is federated=true. Add:
-  //   wiki    — federated (must join unqualified search)
-  //   private — NOT federated (must stay invisible unless explicitly named)
-  //   oldnews — federated but archived (must stay excluded)
-  await engine.executeRaw(
-    `INSERT INTO sources (id, name, local_path, config) VALUES ('wiki', 'wiki', '/tmp/wiki', '{"federated": true}'::jsonb)`,
-  );
-  await engine.executeRaw(
-    `INSERT INTO sources (id, name, local_path, config) VALUES ('private', 'private', '/tmp/private', '{}'::jsonb)`,
-  );
-  await engine.executeRaw(
-    `INSERT INTO sources (id, name, local_path, config, archived) VALUES ('oldnews', 'oldnews', '/tmp/oldnews', '{"federated": true}'::jsonb, true)`,
-  );
-  const pages: Array<[slug: string, sourceId: string, where: string]> = [
-    ['notes/home', 'default', 'default'],
-    ['wiki/topic', 'wiki', 'wiki'],
-    ['private/topic', 'private', 'private'],
-    ['old/topic', 'oldnews', 'oldnews'],
-  ];
-  for (const [slug, sourceId, where] of pages) {
-    await engine.putPage(slug, {
-      type: 'note', title: `Topic in ${where}`, compiled_truth: `the zebra telescope in ${where}`, frontmatter: {},
-    }, { sourceId });
-    await engine.upsertChunks(slug, [
-      { chunk_index: 0, chunk_text: `the zebra telescope in ${where}`, chunk_source: 'compiled_truth' },
-    ], { sourceId });
-  }
-  // Keyword-only search path: no embedding provider needed in tests.
-  await engine.setConfig('search.mcp_keyword_only', 'true');
-}, 60_000);
-
-afterAll(async () => {
-  if (engine) await engine.disconnect();
-}, 60_000);
-
-describe('localFederatedSourceIds — CLI-side scope computation', () => {
-  test('non-explicit tier: resolved source first, then other federated, archived excluded', async () => {
-    expect(await localFederatedSourceIds(engine, 'default', 'seed_default')).toEqual(['default', 'wiki']);
-  });
-
-  test('non-federated resolved source still joins its own scope', async () => {
-    expect(await localFederatedSourceIds(engine, 'private', 'brain_default')).toEqual(['private', 'default', 'wiki']);
-  });
-
-  test('explicit tiers (--source / env / dotfile) never expand', async () => {
-    expect(await localFederatedSourceIds(engine, 'default', 'flag')).toBeUndefined();
-    expect(await localFederatedSourceIds(engine, 'default', 'env')).toBeUndefined();
-    expect(await localFederatedSourceIds(engine, 'default', 'dotfile')).toBeUndefined();
-  });
-
-  test('single federated source (the resolved one) keeps the scalar fast path', async () => {
-    const solo = { executeRaw: async () => [{ id: 'default' }] } as any;
-    expect(await localFederatedSourceIds(solo, 'default', 'seed_default')).toBeUndefined();
-  });
-});
-
-describe('federatedSearchScope — trust + explicitness matrix', () => {
-  test('trusted local + unqualified widens to the federated set', () => {
-    const ctx = ctxOf({ localFederatedSourceIds: ['default', 'wiki'] });
-    expect(federatedSearchScope(ctx)).toEqual({ sourceIds: ['default', 'wiki'] });
-  });
-
-  test('remote caller NEVER widens (fail-closed), even if the field is set', () => {
-    const ctx = ctxOf({ remote: true, localFederatedSourceIds: ['default', 'wiki'] });
-    expect(federatedSearchScope(ctx)).toEqual({ sourceId: 'default' });
-  });
-
-  test('per-call source_id wins over the federated set', () => {
-    const ctx = ctxOf({ localFederatedSourceIds: ['default', 'wiki'] });
-    expect(federatedSearchScope(ctx, 'wiki')).toEqual({ sourceId: 'wiki' });
-  });
-
-  test('per-call __all__ keeps the whole-brain semantics for trusted local', () => {
-    const ctx = ctxOf({ localFederatedSourceIds: ['default', 'wiki'] });
-    expect(federatedSearchScope(ctx, '__all__')).toEqual({});
-  });
-
-  test('a federated OAuth grant wins over the local set', () => {
-    const ctx = ctxOf({
-      localFederatedSourceIds: ['default', 'wiki'],
-      auth: { allowedSources: ['a', 'b'] } as OperationContext['auth'],
-    });
-    expect(federatedSearchScope(ctx)).toEqual({ sourceIds: ['a', 'b'] });
-  });
-
-  test('no local federated set → unchanged scalar scope', () => {
-    expect(federatedSearchScope(ctxOf())).toEqual({ sourceId: 'default' });
-  });
-});
-
-describe('search op — unqualified local search spans federated sources', () => {
-  test('federated source results appear; non-federated + archived stay invisible', async () => {
-    const ctx = ctxOf({
-      localFederatedSourceIds: await localFederatedSourceIds(engine, 'default', 'seed_default'),
-    });
-    const results = (await search.handler(ctx, { query: 'zebra telescope' })) as Array<{ slug: string }>;
-    const slugs = results.map((r) => r.slug);
-    expect(slugs).toContain('notes/home');
-    expect(slugs).toContain('wiki/topic'); // pre-#2561 this was missing
-    expect(slugs).not.toContain('private/topic');
-    expect(slugs).not.toContain('old/topic');
-  });
-
-  test('explicit source resolution (no federated set on ctx) stays single-source', async () => {
-    const results = (await search.handler(ctxOf(), { query: 'zebra telescope' })) as Array<{ slug: string }>;
-    const slugs = results.map((r) => r.slug);
-    expect(slugs).toEqual(['notes/home']);
-  });
-});

test/remediation-context-extraction-lag.test.ts

@@ -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);
+  });
+});

test/remediation-run-d7-refresh.serial.test.ts

@@ -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);
+  });
+});