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/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/commands/doctor.ts

@@ -820,10 +820,6 @@ export async function doctorReportRemote(engine: BrainEngine): Promise<DoctorRep
   // v0.42.x (#1794, 4A): pool-budget nudge when GBRAIN_MAX_CONNECTIONS is set.
   checks.push(await checkPoolBudget(engine));
 
-  // #2552: warn when an explicit embed-concurrency override fans out against
-  // a local single-slot embedding endpoint (silent backfill starvation).
-  checks.push(await checkEmbedConcurrency());
-
   // v0.42.7 (#1696): link-extraction lag. Strictly SQL (single indexed COUNT),
   // safe on the thin-client/remote path — remote operators on checkout-less
   // Postgres brains are exactly who can't otherwise see the extraction backlog.
@@ -3819,61 +3815,6 @@ export function computePoolBudgetCheck(
   };
 }
 
-/**
- * #2552: warn when an explicit GBRAIN_EMBED_CONCURRENCY override fans out
- * against a local single-slot embedding endpoint (Ollama / llama-server /
- * localhost base URL). Requests serialize on the one loaded model, so N
- * parallel pages multiply latency xN and can exceed the fetch timeout with
- * no surfaced error — the backfill silently starves. (When the env var is
- * unset, embed auto-caps at LOCAL_EMBED_CONCURRENCY_CAP and this check
- * reports ok.) Pure; exported for tests.
- */
-export function computeEmbedConcurrencyCheck(
-  isLocalEndpoint: boolean,
-  envValue: string | undefined,
-  localCap: number,
-): Check {
-  const name = 'embed_concurrency';
-  if (!isLocalEndpoint) {
-    return { name, status: 'ok', message: 'Embedding endpoint is not a local inference server — cloud concurrency defaults apply.' };
-  }
-  const parsed = envValue ? parseInt(envValue, 10) : NaN;
-  if (envValue && Number.isFinite(parsed) && parsed > localCap) {
-    return {
-      name,
-      status: 'warn',
-      message:
-        `GBRAIN_EMBED_CONCURRENCY=${parsed} against a local embedding endpoint. ` +
-        `Local inference servers serialize requests, so ${parsed} parallel pages multiply ` +
-        `latency x${parsed} and can exceed the fetch timeout — the embed backfill stalls ` +
-        `with no error. Unset GBRAIN_EMBED_CONCURRENCY (auto-caps at ${localCap}) or set it <= ${localCap}.`,
-    };
-  }
-  return {
-    name,
-    status: 'ok',
-    message: `Local embedding endpoint detected; embed concurrency capped at ${envValue ? parsed : localCap}.`,
-  };
-}
-
-/** Thin gateway/env wrapper over `computeEmbedConcurrencyCheck`. */
-export async function checkEmbedConcurrency(): Promise<Check> {
-  try {
-    const { isLocalEmbeddingEndpoint, LOCAL_EMBED_CONCURRENCY_CAP } = await import('../core/ai/gateway.ts');
-    return computeEmbedConcurrencyCheck(
-      isLocalEmbeddingEndpoint(),
-      process.env.GBRAIN_EMBED_CONCURRENCY,
-      LOCAL_EMBED_CONCURRENCY_CAP,
-    );
-  } catch (err) {
-    return {
-      name: 'embed_concurrency',
-      status: 'ok',
-      message: `Skipped (${err instanceof Error ? err.message : String(err)})`,
-    };
-  }
-}
-
 /** Thin env/engine wrapper over `computePoolBudgetCheck`. */
 export async function checkPoolBudget(_engine: BrainEngine): Promise<Check> {
   try {

src/commands/embed.ts

@@ -1,6 +1,5 @@
 import type { BrainEngine } from '../core/engine.ts';
 import { embedBatch, currentEmbeddingSignature } from '../core/embedding.ts';
-import { isLocalEmbeddingEndpoint, LOCAL_EMBED_CONCURRENCY_CAP } from '../core/ai/gateway.ts';
 import type { ChunkInput } from '../core/types.ts';
 import { chunkText } from '../core/chunkers/recursive.ts';
 import { createProgress, type ProgressReporter } from '../core/progress.ts';
@@ -177,31 +176,6 @@ export class EmbeddingDimMismatchError extends Error {
   }
 }
 
-/**
- * #2552: resolve the bulk-embed worker count. Env override or the
- * cloud-tuned default of 20 — but when the operator did NOT set
- * GBRAIN_EMBED_CONCURRENCY and the embedding endpoint is a local inference
- * server (Ollama / llama-server / localhost base URL), cap at
- * LOCAL_EMBED_CONCURRENCY_CAP: 20 parallel pages against a single-slot
- * server serialize on the one loaded model, multiply latency x20 past the
- * fetch timeout, and starve the backfill with no surfaced error. An
- * explicit env value always wins (`gbrain doctor` warns instead).
- * Pacing only ever LOWERS concurrency (Codex P2).
- */
-export function resolveEmbedConcurrency(paceMaxConcurrency?: number): number {
-  const envSet = !!process.env.GBRAIN_EMBED_CONCURRENCY;
-  const base = parseInt(process.env.GBRAIN_EMBED_CONCURRENCY || '20', 10);
-  let resolved = base;
-  if (!envSet && isLocalEmbeddingEndpoint() && base > LOCAL_EMBED_CONCURRENCY_CAP) {
-    resolved = LOCAL_EMBED_CONCURRENCY_CAP;
-    serr(
-      `[embed] local embedding endpoint detected — capping concurrency at ` +
-      `${LOCAL_EMBED_CONCURRENCY_CAP} (set GBRAIN_EMBED_CONCURRENCY to override)`,
-    );
-  }
-  return paceMaxConcurrency ? Math.min(resolved, paceMaxConcurrency) : resolved;
-}
-
 /**
  * Pre-flight check: read the actual schema column dim and compare to the
  * gateway's resolved dim. Throws `EmbeddingDimMismatchError` on mismatch
@@ -703,8 +677,10 @@ async function embedAll(
   // Paced runs lower this to the resolved cap (the real lever vs pooler-slot
   // starvation); unpaced keeps the env/default 20. Codex P2: only ever LOWER —
   // never raise above an operator's existing env cap.
-  // #2552: local endpoints auto-cap — see resolveEmbedConcurrency.
-  const CONCURRENCY = resolveEmbedConcurrency(staleOpts?.paceMaxConcurrency);
+  const BASE_CONCURRENCY = parseInt(process.env.GBRAIN_EMBED_CONCURRENCY || '20', 10);
+  const CONCURRENCY = staleOpts?.paceMaxConcurrency
+    ? Math.min(BASE_CONCURRENCY, staleOpts.paceMaxConcurrency)
+    : BASE_CONCURRENCY;
 
   async function embedOnePage(page: typeof pages[number]) {
     // #1737: bail before doing any work for this page if the run was aborted.
@@ -879,8 +855,10 @@ async function embedAllStale(
   // Paced runs lower concurrency to the resolved cap (E-1: worker count IS the
   // lever on this single pool, no separate permit). Codex P2: pacing only ever
   // LOWERS concurrency — never raise above an operator's existing env cap.
-  // #2552: local endpoints auto-cap — see resolveEmbedConcurrency.
-  const CONCURRENCY = resolveEmbedConcurrency(staleOpts?.paceMaxConcurrency);
+  const BASE_CONCURRENCY = parseInt(process.env.GBRAIN_EMBED_CONCURRENCY || '20', 10);
+  const CONCURRENCY = staleOpts?.paceMaxConcurrency
+    ? Math.min(BASE_CONCURRENCY, staleOpts.paceMaxConcurrency)
+    : BASE_CONCURRENCY;
   const pacer = staleOpts?.pacer ?? createNoopPacer();
 
   // D3 + D3a + D8: wall-clock budget. 30 min default; env override.

src/core/ai/gateway.ts

@@ -683,33 +683,6 @@ export function getEmbeddingDimensions(): number {
   return requireConfig().embedding_dimensions ?? DEFAULT_EMBEDDING_DIMENSIONS;
 }
 
-/**
- * #2552: cap for parallel bulk-embed workers against a local inference
- * server. A single-slot Ollama/llama-server serializes requests, so the
- * cloud-tuned 20-worker fan-out multiplies latency x20 and blows past the
- * fetch timeout with no surfaced error (the backfill silently starves).
- */
-export const LOCAL_EMBED_CONCURRENCY_CAP = 2;
-
-/**
- * #2552: true when the configured embedding model routes to a local
- * inference server — the `ollama` / `llama-server` recipes, or any recipe
- * whose base URL was explicitly pointed at localhost. Bulk callers use this
- * to pick CPU-safe concurrency defaults; `gbrain doctor` uses it to warn
- * about an explicit cloud-sized override. Fail-open: unconfigured or
- * unresolvable gateway → false (cloud behavior, the historical default).
- */
-export function isLocalEmbeddingEndpoint(): boolean {
-  try {
-    const { recipe } = resolveRecipe(getEmbeddingModel());
-    if (recipe.id === 'ollama' || recipe.id === 'llama-server') return true;
-    const base = requireConfig().base_urls?.[recipe.id] ?? '';
-    return /\/\/(localhost|127\.0\.0\.1|\[::1\])(:|\/|$)/i.test(base);
-  } catch {
-    return false;
-  }
-}
-
 /**
  * v0.28.11: returns the configured multimodal embedding model when set,
  * or undefined if the brain falls back to `embedding_model` for multimodal

src/core/ai/recipes/ollama.ts

@@ -29,17 +29,9 @@ export const ollama: Recipe = {
       trust_custom_dims: true, // #2271: local models carry varied native dims
       cost_per_1m_tokens_usd: 0,
       price_last_verified: '2026-04-20',
-      // #2552: Ollama's true batch capacity depends on the locally loaded
-      // model + OLLAMA_NUM_PARALLEL, but the previous `no_batch_cap: true`
-      // meant a whole page went out in ONE request — on a CPU-only box that
-      // multiplies latency past the fetch timeout and the backfill starves
-      // with no surfaced error. Ollama doesn't return a recognizable
-      // token-limit error either, so the recursive-halving safety net never
-      // fires; a conservative static pre-split cap is the only guard.
-      // 4096 tokens x 2 chars/token ~= 8K chars per request (code-dense
-      // pages run ~2 chars/token, not the tiktoken-ish 4).
-      max_batch_tokens: 4096,
-      chars_per_token: 2,
+      // Ollama's batch capacity depends on the locally loaded model + the
+      // OLLAMA_NUM_PARALLEL config; no static cap to declare. v0.32 (#779).
+      no_batch_cap: true,
     },
   },
   setup_hint: 'Install Ollama from https://ollama.ai, then `ollama pull nomic-embed-text` and `ollama serve`.',

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/doctor-categories.ts

@@ -141,7 +141,6 @@ export const OPS_CHECK_NAMES: ReadonlySet<string> = new Set([
   'pgbouncer_prepare',
   'pgvector',
   'pool_budget',
-  'embed_concurrency',
   'progressive_batch_audit_health',
   'queue_health',
   'reranker_health',

src/core/pglite-engine.ts

@@ -56,7 +56,7 @@ import { GBrainError, PAGE_SORT_SQL, ENRICH_ORDER_SQL } from './types.ts';
 import { finalizeLastSeen } from './chronicle/last-seen.ts';
 import { computeAnomaliesFromBuckets } from './cycle/anomaly.ts';
 import { resolveBoostMap, resolveHardExcludes } from './search/source-boost.ts';
-import { buildSourceFactorCase, buildHardExcludeClause, buildVisibilityClause, buildRecencyComponentSql, buildBestPerPagePoolCte, buildOrFallbackWebsearchQuery, buildWebsearchQueryExpr } from './search/sql-ranking.ts';
+import { buildSourceFactorCase, buildHardExcludeClause, buildVisibilityClause, buildRecencyComponentSql, buildBestPerPagePoolCte, buildOrFallbackWebsearchQuery } from './search/sql-ranking.ts';
 import {
   normalizeEngineColumn,
   buildVectorCastFragment,
@@ -1591,8 +1591,6 @@ export class PGLiteEngine implements BrainEngine {
     }
 
     // v0.20.0 Cathedral II Layer 10 C1/C2: language + symbol-kind filters.
-    // #2380: slash-bearing queries match both the split-word and literal
-    // slash forms — see buildWebsearchQueryExpr in ./search/sql-ranking.ts.
     const params: unknown[] = [query, innerLimit, limit, offset];
     let extraFilter = '';
     if (opts?.language) {
@@ -1632,7 +1630,6 @@ export class PGLiteEngine implements BrainEngine {
     // FTS config name (e.g. 'english', 'pt_br'). Validated by getFtsLanguage()
     // — safe to interpolate into raw SQL.
     const ftsLang = getFtsLanguage();
-    const ftsQueryExpr = buildWebsearchQueryExpr(ftsLang, '$1', query);
 
     const keywordSql =
       `WITH ranked AS (
@@ -1640,14 +1637,14 @@ export class PGLiteEngine implements BrainEngine {
            p.slug, p.id as page_id, p.title, p.type, p.source_id,
            p.effective_date, p.effective_date_source,
            cc.id as chunk_id, cc.chunk_index, cc.chunk_text, cc.chunk_source,
-           ts_rank(cc.search_vector, ${ftsQueryExpr}) * ${sourceFactorCase} AS score,
+           ts_rank(cc.search_vector, websearch_to_tsquery('${ftsLang}', $1)) * ${sourceFactorCase} AS score,
            CASE WHEN p.updated_at < (
              SELECT MAX(te.created_at) FROM timeline_entries te WHERE te.page_id = p.id
            ) THEN true ELSE false END AS stale
          FROM content_chunks cc
          JOIN pages p ON p.id = cc.page_id
          JOIN sources s ON s.id = p.source_id
-         WHERE cc.search_vector @@ ${ftsQueryExpr} ${detailFilter}${extraFilter} ${hardExcludeClause} ${visibilityClause}
+         WHERE cc.search_vector @@ websearch_to_tsquery('${ftsLang}', $1) ${detailFilter}${extraFilter} ${hardExcludeClause} ${visibilityClause}
            -- v0.27.1: hide image rows from default text-keyword search so
            -- OCR text doesn't drown text-page hits. Image-similarity queries
            -- run a separate vector path on embedding_image.
@@ -1715,10 +1712,7 @@ export class PGLiteEngine implements BrainEngine {
     // FTS config name (e.g. 'english', 'pt_br'). Validated by getFtsLanguage()
     // — safe to interpolate into raw SQL.
     const ftsLang = getFtsLanguage();
-    const ftsQueryExpr = buildWebsearchQueryExpr(ftsLang, '$1', query);
 
-    // #2380: slash-bearing queries match both the split-word and literal
-    // slash forms — see buildWebsearchQueryExpr in ./search/sql-ranking.ts.
     const params: unknown[] = [query, limit, offset];
     let extraFilter = '';
     if (opts?.type) {
@@ -1766,7 +1760,7 @@ export class PGLiteEngine implements BrainEngine {
          COALESCE(rep.chunk_index, 0) as chunk_index,
          COALESCE(rep.chunk_text, '') as chunk_text,
          COALESCE(rep.chunk_source, 'compiled_truth') as chunk_source,
-         ts_rank_cd(p.search_vector, ${ftsQueryExpr}) * ${sourceFactorCase} AS score,
+         ts_rank_cd(p.search_vector, websearch_to_tsquery('${ftsLang}', $1)) * ${sourceFactorCase} AS score,
          CASE WHEN p.updated_at < (
            SELECT MAX(te.created_at) FROM timeline_entries te WHERE te.page_id = p.id
          ) THEN true ELSE false END AS stale
@@ -1781,7 +1775,7 @@ export class PGLiteEngine implements BrainEngine {
          ORDER BY (cc.chunk_source = 'compiled_truth') DESC, cc.chunk_index ASC
          LIMIT 1
        ) rep ON true
-       WHERE p.search_vector @@ ${ftsQueryExpr}
+       WHERE p.search_vector @@ websearch_to_tsquery('${ftsLang}', $1)
          ${extraFilter} ${hardExcludeClause} ${visibilityClause}
        ORDER BY score DESC, p.id ASC
        LIMIT $2 OFFSET $3`;
@@ -1968,8 +1962,6 @@ export class PGLiteEngine implements BrainEngine {
       });
     }
 
-    // #2380: slash-bearing queries match both the split-word and literal
-    // slash forms — see buildWebsearchQueryExpr in ./search/sql-ranking.ts.
     const params: unknown[] = [query, limit, offset];
     let extraFilter = '';
     if (opts?.language) {
@@ -2004,21 +1996,20 @@ export class PGLiteEngine implements BrainEngine {
     // FTS config name (e.g. 'english', 'pt_br'). Validated by getFtsLanguage()
     // — safe to interpolate into raw SQL.
     const ftsLang = getFtsLanguage();
-    const ftsQueryExpr = buildWebsearchQueryExpr(ftsLang, '$1', query);
 
     const { rows } = await this.db.query(
       `SELECT
          p.slug, p.id as page_id, p.title, p.type, p.source_id,
          p.effective_date, p.effective_date_source,
          cc.id as chunk_id, cc.chunk_index, cc.chunk_text, cc.chunk_source,
-         ts_rank(cc.search_vector, ${ftsQueryExpr}) * ${sourceFactorCase} AS score,
+         ts_rank(cc.search_vector, websearch_to_tsquery('${ftsLang}', $1)) * ${sourceFactorCase} AS score,
          CASE WHEN p.updated_at < (
            SELECT MAX(te.created_at) FROM timeline_entries te WHERE te.page_id = p.id
          ) THEN true ELSE false END AS stale
        FROM content_chunks cc
        JOIN pages p ON p.id = cc.page_id
        JOIN sources s ON s.id = p.source_id
-       WHERE cc.search_vector @@ ${ftsQueryExpr} ${detailFilter}${extraFilter} ${hardExcludeClause} ${visibilityClause}
+       WHERE cc.search_vector @@ websearch_to_tsquery('${ftsLang}', $1) ${detailFilter}${extraFilter} ${hardExcludeClause} ${visibilityClause}
        ORDER BY score DESC
        LIMIT $2 OFFSET $3`,
       params

src/core/postgres-engine.ts

@@ -64,7 +64,7 @@ import { ConnectionManager } from './connection-manager.ts';
 import { logConnectionEvent } from './connection-audit.ts';
 import { validateSlug, contentHash, rowToPage, rowToStalePage, rowToChunk, rowToSearchResult, parseEmbedding, tryParseEmbedding, takeRowToTake, takeHitRowToHit, isUndefinedTableError, warnOncePerProcess } from './utils.ts';
 import { resolveBoostMap, resolveHardExcludes } from './search/source-boost.ts';
-import { buildSourceFactorCase, buildHardExcludeClause, buildVisibilityClause, buildRecencyComponentSql, buildBestPerPagePoolCte, buildOrFallbackWebsearchQuery, buildWebsearchQueryExpr } from './search/sql-ranking.ts';
+import { buildSourceFactorCase, buildHardExcludeClause, buildVisibilityClause, buildRecencyComponentSql, buildBestPerPagePoolCte, buildOrFallbackWebsearchQuery } from './search/sql-ranking.ts';
 import { DEFAULT_EMBEDDING_MODEL, DEFAULT_EMBEDDING_DIMENSIONS } from './ai/defaults.ts';
 import { DELETE_BATCH_SIZE } from './engine-constants.ts';
 
@@ -1691,8 +1691,6 @@ export class PostgresEngine implements BrainEngine {
     const hardExcludePrefixes = resolveHardExcludes(opts?.exclude_slug_prefixes, opts?.include_slug_prefixes);
     const hardExcludeClause = buildHardExcludeClause('p.slug', hardExcludePrefixes);
 
-    // #2380: slash-bearing queries match both the split-word and literal
-    // slash forms — see buildWebsearchQueryExpr in ./search/sql-ranking.ts.
     const params: unknown[] = [query];
     let typeClause = '';
     if (type) {
@@ -1763,7 +1761,6 @@ export class PostgresEngine implements BrainEngine {
     // FTS config name (e.g. 'english', 'pt_br'). Validated by getFtsLanguage()
     // — safe to interpolate into raw SQL.
     const ftsLang = getFtsLanguage();
-    const ftsQueryExpr = buildWebsearchQueryExpr(ftsLang, '$1', query);
 
     const rawQuery = `
       WITH ranked_chunks AS (
@@ -1771,11 +1768,11 @@ export class PostgresEngine implements BrainEngine {
           p.slug, p.id as page_id, p.title, p.type, p.source_id,
           p.effective_date, p.effective_date_source,
           cc.id as chunk_id, cc.chunk_index, cc.chunk_text, cc.chunk_source,
-          ts_rank(cc.search_vector, ${ftsQueryExpr}) * ${sourceFactorCase} AS score
+          ts_rank(cc.search_vector, websearch_to_tsquery('${ftsLang}', $1)) * ${sourceFactorCase} AS score
         FROM content_chunks cc
         JOIN pages p ON p.id = cc.page_id
         JOIN sources s ON s.id = p.source_id
-        WHERE cc.search_vector @@ ${ftsQueryExpr}
+        WHERE cc.search_vector @@ websearch_to_tsquery('${ftsLang}', $1)
           ${typeClause}
           ${typesClause}
           ${excludeSlugsClause}
@@ -1866,10 +1863,7 @@ export class PostgresEngine implements BrainEngine {
     // FTS config name (e.g. 'english', 'pt_br'). Validated by getFtsLanguage()
     // — safe to interpolate into raw SQL.
     const ftsLang = getFtsLanguage();
-    const ftsQueryExpr = buildWebsearchQueryExpr(ftsLang, '$1', query);
 
-    // #2380: slash-bearing queries match both the split-word and literal
-    // slash forms — see buildWebsearchQueryExpr in ./search/sql-ranking.ts.
     const params: unknown[] = [query];
     let typeClause = '';
     if (opts?.type) {
@@ -1929,7 +1923,7 @@ export class PostgresEngine implements BrainEngine {
         COALESCE(rep.chunk_index, 0) as chunk_index,
         COALESCE(rep.chunk_text, '') as chunk_text,
         COALESCE(rep.chunk_source, 'compiled_truth') as chunk_source,
-        ts_rank_cd(p.search_vector, ${ftsQueryExpr}) * ${sourceFactorCase} AS score,
+        ts_rank_cd(p.search_vector, websearch_to_tsquery('${ftsLang}', $1)) * ${sourceFactorCase} AS score,
         false AS stale
       FROM pages p
       JOIN sources s ON s.id = p.source_id
@@ -1942,7 +1936,7 @@ export class PostgresEngine implements BrainEngine {
         ORDER BY (cc.chunk_source = 'compiled_truth') DESC, cc.chunk_index ASC
         LIMIT 1
       ) rep ON true
-      WHERE p.search_vector @@ ${ftsQueryExpr}
+      WHERE p.search_vector @@ websearch_to_tsquery('${ftsLang}', $1)
         ${typeClause}
         ${typesClause}
         ${excludeSlugsClause}
@@ -2006,8 +2000,6 @@ export class PostgresEngine implements BrainEngine {
     const hardExcludePrefixes = resolveHardExcludes(opts?.exclude_slug_prefixes, opts?.include_slug_prefixes);
     const hardExcludeClause = buildHardExcludeClause('p.slug', hardExcludePrefixes);
 
-    // #2380: slash-bearing queries match both the split-word and literal
-    // slash forms — see buildWebsearchQueryExpr in ./search/sql-ranking.ts.
     const params: unknown[] = [query];
     let typeClause = '';
     if (type) {
@@ -2068,19 +2060,18 @@ export class PostgresEngine implements BrainEngine {
     // FTS config name (e.g. 'english', 'pt_br'). Validated by getFtsLanguage()
     // — safe to interpolate into raw SQL.
     const ftsLang = getFtsLanguage();
-    const ftsQueryExpr = buildWebsearchQueryExpr(ftsLang, '$1', query);
 
     const rawQuery = `
       SELECT
         p.slug, p.id as page_id, p.title, p.type, p.source_id,
         p.effective_date, p.effective_date_source,
         cc.id as chunk_id, cc.chunk_index, cc.chunk_text, cc.chunk_source,
-        ts_rank(cc.search_vector, ${ftsQueryExpr}) * ${sourceFactorCase} AS score,
+        ts_rank(cc.search_vector, websearch_to_tsquery('${ftsLang}', $1)) * ${sourceFactorCase} AS score,
         false AS stale
       FROM content_chunks cc
       JOIN pages p ON p.id = cc.page_id
       JOIN sources s ON s.id = p.source_id
-      WHERE cc.search_vector @@ ${ftsQueryExpr}
+      WHERE cc.search_vector @@ websearch_to_tsquery('${ftsLang}', $1)
         ${typeClause}
         ${typesClause}
         ${excludeSlugsClause}

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/search/sql-ranking.ts

@@ -251,28 +251,6 @@ export function buildOrFallbackWebsearchQuery(query: string): string | null {
   return tokens.join(' OR ');
 }
 
-/**
- * #2380: FTS query expression for slash-bearing queries. Postgres' default
- * text-search parser classifies `foo/bar` as a single `file`-alias lexeme —
- * on BOTH the query side and the index side. So a raw `foo/bar` query only
- * matched documents carrying the identical joined lexeme (literal paths),
- * and a slash-split query only matches documents whose text had the words
- * separated. Neither form alone covers both document shapes; OR the two
- * parses so a slash query matches prose ("foo and bar", stemmed, AND
- * semantics) AND literal slash forms ("src/core/x.ts") alike.
- *
- * Slash-free queries return the plain single-parse expression — byte-
- * identical SQL and identical ts_rank to the historical behavior.
- *
- * `ftsLang` is validated by getFtsLanguage() (safe to interpolate);
- * `param` is a `$N` placeholder, never user text.
- */
-export function buildWebsearchQueryExpr(ftsLang: string, param: string, query: string): string {
-  const plain = `websearch_to_tsquery('${ftsLang}', ${param})`;
-  if (!query.includes('/')) return plain;
-  return `(websearch_to_tsquery('${ftsLang}', translate(${param}, '/', ' ')) || ${plain})`;
-}
-
 // ============================================================
 // v0.29.1 — Recency component SQL builder
 // ============================================================

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/ai/no-batch-cap-suppression.serial.test.ts

@@ -28,8 +28,8 @@ describe('v0.32 #779: no_batch_cap suppresses the missing-max_batch_tokens warni
     resetGateway();
   });
 
-  test('LiteLLM and llama-server declare no_batch_cap: true', () => {
-    for (const id of ['litellm', 'llama-server']) {
+  test('Ollama, LiteLLM, llama-server all declare no_batch_cap: true', () => {
+    for (const id of ['ollama', 'litellm', 'llama-server']) {
       const r = getRecipe(id);
       expect(r, `${id} not registered`).toBeDefined();
       expect(
@@ -39,18 +39,6 @@ describe('v0.32 #779: no_batch_cap suppresses the missing-max_batch_tokens warni
     }
   });
 
-  test('#2552: Ollama declares a conservative static batch cap, not no_batch_cap', () => {
-    // A CPU-only Ollama box wedges when a whole page ships in one request;
-    // Ollama never returns a token-limit error so the recursive-halving
-    // safety net can't fire. The pre-split cap is the only guard.
-    const r = getRecipe('ollama');
-    expect(r).toBeDefined();
-    const e = r!.touchpoints.embedding!;
-    expect(e.no_batch_cap).toBeUndefined();
-    expect(e.max_batch_tokens).toBe(4096);
-    expect(e.chars_per_token).toBe(2);
-  });
-
   test('configureGateway does NOT warn for ollama/litellm/llama-server', () => {
     warnSpy.mockClear();
     resetGateway();

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/embed-local-endpoint.serial.test.ts

@@ -1,118 +0,0 @@
-/**
- * #2552: cloud-tuned embedding defaults silently wedge CPU-only local
- * endpoints (Ollama). Three-part fix under test:
- *
- *  1. `isLocalEmbeddingEndpoint()` — gateway helper detecting local
- *     inference servers (ollama / llama-server recipes, localhost base URL).
- *  2. `resolveEmbedConcurrency()` — embed auto-caps the 20-worker fan-out
- *     at LOCAL_EMBED_CONCURRENCY_CAP for local endpoints unless the
- *     operator set GBRAIN_EMBED_CONCURRENCY explicitly.
- *  3. `computeEmbedConcurrencyCheck()` — doctor warns when an explicit env
- *     override fans out against a local endpoint.
- *
- * Serial: mutates process.env and the module-global gateway config.
- */
-
-import { afterAll, afterEach, describe, expect, test } from 'bun:test';
-import {
-  configureGateway,
-  resetGateway,
-  isLocalEmbeddingEndpoint,
-  LOCAL_EMBED_CONCURRENCY_CAP,
-} from '../src/core/ai/gateway.ts';
-import { resolveEmbedConcurrency } from '../src/commands/embed.ts';
-import { computeEmbedConcurrencyCheck } from '../src/commands/doctor.ts';
-
-const SAVED_ENV = process.env.GBRAIN_EMBED_CONCURRENCY;
-
-afterEach(() => {
-  resetGateway();
-  if (SAVED_ENV === undefined) delete process.env.GBRAIN_EMBED_CONCURRENCY;
-  else process.env.GBRAIN_EMBED_CONCURRENCY = SAVED_ENV;
-});
-
-afterAll(() => {
-  resetGateway();
-});
-
-describe('#2552 isLocalEmbeddingEndpoint', () => {
-  test('false when the gateway is not configured (fail-open to cloud behavior)', () => {
-    resetGateway();
-    expect(isLocalEmbeddingEndpoint()).toBe(false);
-  });
-
-  test('true for the ollama recipe', () => {
-    configureGateway({ embedding_model: 'ollama:nomic-embed-text', env: {} });
-    expect(isLocalEmbeddingEndpoint()).toBe(true);
-  });
-
-  test('true for the llama-server recipe', () => {
-    configureGateway({ embedding_model: 'llama-server:my-gguf', env: {} });
-    expect(isLocalEmbeddingEndpoint()).toBe(true);
-  });
-
-  test('false for a cloud recipe', () => {
-    configureGateway({
-      embedding_model: 'openai:text-embedding-3-small',
-      env: { OPENAI_API_KEY: 'fake' },
-    });
-    expect(isLocalEmbeddingEndpoint()).toBe(false);
-  });
-
-  test('true when a cloud recipe base URL is explicitly pointed at localhost', () => {
-    configureGateway({
-      embedding_model: 'openai:text-embedding-3-small',
-      env: { OPENAI_API_KEY: 'fake' },
-      base_urls: { openai: 'http://localhost:8080/v1' },
-    });
-    expect(isLocalEmbeddingEndpoint()).toBe(true);
-  });
-});
-
-describe('#2552 resolveEmbedConcurrency', () => {
-  test('caps at LOCAL_EMBED_CONCURRENCY_CAP for a local endpoint when env is unset', () => {
-    delete process.env.GBRAIN_EMBED_CONCURRENCY;
-    configureGateway({ embedding_model: 'ollama:nomic-embed-text', env: {} });
-    expect(resolveEmbedConcurrency()).toBe(LOCAL_EMBED_CONCURRENCY_CAP);
-  });
-
-  test('explicit env override always wins, even against a local endpoint', () => {
-    process.env.GBRAIN_EMBED_CONCURRENCY = '10';
-    configureGateway({ embedding_model: 'ollama:nomic-embed-text', env: {} });
-    expect(resolveEmbedConcurrency()).toBe(10);
-  });
-
-  test('cloud endpoints keep the historical default of 20', () => {
-    delete process.env.GBRAIN_EMBED_CONCURRENCY;
-    configureGateway({ env: { OPENAI_API_KEY: 'fake' } });
-    expect(resolveEmbedConcurrency()).toBe(20);
-  });
-
-  test('pacing only ever lowers concurrency', () => {
-    delete process.env.GBRAIN_EMBED_CONCURRENCY;
-    configureGateway({ embedding_model: 'ollama:nomic-embed-text', env: {} });
-    expect(resolveEmbedConcurrency(1)).toBe(1);
-    expect(resolveEmbedConcurrency(16)).toBe(LOCAL_EMBED_CONCURRENCY_CAP);
-  });
-});
-
-describe('#2552 computeEmbedConcurrencyCheck (doctor)', () => {
-  test('ok for non-local endpoints', () => {
-    expect(computeEmbedConcurrencyCheck(false, '20', 2).status).toBe('ok');
-  });
-
-  test('warn when an explicit override exceeds the local cap', () => {
-    const check = computeEmbedConcurrencyCheck(true, '20', 2);
-    expect(check.status).toBe('warn');
-    expect(check.message).toContain('GBRAIN_EMBED_CONCURRENCY=20');
-  });
-
-  test('ok when env is unset against a local endpoint (auto-cap applies)', () => {
-    expect(computeEmbedConcurrencyCheck(true, undefined, 2).status).toBe('ok');
-  });
-
-  test('ok when the override is at or under the cap', () => {
-    expect(computeEmbedConcurrencyCheck(true, '2', 2).status).toBe('ok');
-    expect(computeEmbedConcurrencyCheck(true, '1', 2).status).toBe('ok');
-  });
-});

test/pglite-engine.test.ts

@@ -216,67 +216,6 @@ describe('PGLiteEngine: Search', () => {
     expect(results.length).toBe(0);
   });
 
-  // Regression (#2380): queries containing `/` used to bypass FTS AND
-  // semantics. Postgres' default text-search parser classifies `foo/bar` as
-  // a `file`-alias token mapped to the `simple` dictionary, so it became a
-  // single un-stemmed lexeme `'foo/bar'` that never matches indexed text —
-  // the primary FTS pass returned 0 and the OR fallback took over, matching
-  // pages that contain EITHER term. searchKeyword/searchTitles now normalize
-  // `/` to whitespace before websearch_to_tsquery parses, so the primary
-  // AND pass matches directly.
-  test('searchKeyword: slash query matches with AND semantics, not OR fallback', async () => {
-    // Decoy shares only ONE of the two query terms ('enterprise').
-    await engine.putPage('concepts/enterprise-pricing', {
-      type: 'concept', title: 'Widget Pricing',
-      compiled_truth: 'Enterprise pricing for widgets.',
-    });
-    await engine.upsertChunks('concepts/enterprise-pricing', [
-      { chunk_index: 0, chunk_text: 'Enterprise pricing for widgets', chunk_source: 'compiled_truth' },
-    ]);
-
-    // Both terms co-occur only in the novamind chunk. Pre-fix this returned
-    // BOTH pages (primary pass zero-hit → OR fallback); post-fix the primary
-    // AND pass returns exactly the co-occurrence page.
-    const results = await engine.searchKeyword('NovaMind/enterprise');
-    expect(results.length).toBe(1);
-    expect(results[0].slug).toBe('companies/novamind');
-  });
-
-  test('searchTitles: slash query matches with AND semantics, not OR fallback', async () => {
-    await engine.putPage('companies/novamind-enterprise', {
-      type: 'company', title: 'NovaMind Enterprise Platform',
-      compiled_truth: 'Placeholder body.',
-    });
-    await engine.putPage('guides/enterprise-sales', {
-      type: 'concept', title: 'Enterprise Sales Guide',
-      compiled_truth: 'Placeholder body.',
-    });
-
-    // Pre-fix: `NovaMind/Enterprise` parsed as one file-alias lexeme → the
-    // primary title pass returned 0 and the OR fallback matched BOTH titles.
-    const results = await engine.searchTitles('NovaMind/Enterprise');
-    expect(results.length).toBe(1);
-    expect(results[0].slug).toBe('companies/novamind-enterprise');
-  });
-
-  test('searchKeyword: slash query still matches the literal slash form (file paths)', async () => {
-    // The INDEX side also emits the joined file-alias lexeme for literal
-    // `foo/bar` text, so a query normalized to split words alone would go
-    // blind to documents containing the literal slash form (paths, URLs).
-    // buildWebsearchQueryExpr ORs both parses; this pins the raw arm.
-    await engine.putPage('runbooks/widget-deploy', {
-      type: 'concept', title: 'Widget Deploy Runbook',
-      compiled_truth: 'Runbook for the acme/widget deployment pipeline.',
-    });
-    await engine.upsertChunks('runbooks/widget-deploy', [
-      { chunk_index: 0, chunk_text: 'Runbook for the acme/widget deployment pipeline', chunk_source: 'compiled_truth' },
-    ]);
-
-    const results = await engine.searchKeyword('acme/widget');
-    expect(results.length).toBe(1);
-    expect(results[0].slug).toBe('runbooks/widget-deploy');
-  });
-
   test('tsvector trigger populates search_vector on insert', async () => {
     // Verify the PL/pgSQL trigger fires and content_chunks.search_vector is
     // populated from chunk_text. v0.20.0 Cathedral II Layer 3 moved FTS from

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);
+  });
+});